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

    Neuronpedia

    INDEX
    Explanations

    superlative expressions indicating the highest degree or level of something

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

    "most" followed by an adjective

    np_acts-logits-general · gemini-2.0-flash

    most followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     étoit
    -0.72
     refroid
    -0.69
     avoient
    -0.67
     quelcon
    -0.63
     médié
    -0.62
     âgées
    -0.61
     ['./
    -0.60
     cáps
    -0.59
     giovan
    -0.57
     supérieures
    -0.57
    POSITIVE LOGITS
    %"),
    0.71
    thest
    0.69
     amount
    0.67
    tanleria
    0.66
     Moles
    0.64
    ✨:
    0.61
    ContentAsync
    0.61
    HEAST
    0.60
    ?»
    0.59
    .」
    0.59
    Act Density 0.107%

    No Known Activations