Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to abilities, challenges, and experiences of individuals, especially in the context of teamwork or support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows nouns describing abstract qualities

    np_acts-logits-general · gemini-2.0-flash

    abstract concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     صوتيه
    -0.60
     GenerationType
    -0.57
    twimg
    -0.52
    medriver
    -0.51
    WriteTagHelper
    -0.50
    WebVitals
    -0.50
    tonode
    -0.49
     المعيارى
    -0.49
     الحره
    -0.47
    StoryboardSegue
    -0.46
    POSITIVE LOGITS
    TokenNameLBRACE
    0.51
    liceerd
    0.51
    ⓧ
    0.50
     seemingly
    0.48
     Chwiliwch
    0.44
    +:+
    0.44
     eens
    0.42
    ⤹
    0.41
    ffilm
    0.41
     “…
    0.41
    Act Density 0.578%

    No Known Activations