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

    Neuronpedia

    INDEX
    Explanations

    present participles and past tense verbs in various contexts

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

    Followed by adverbs or punctuation

    np_acts-logits-general · gemini-2.0-flash

    heaving heavily, shining ultraviolet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.43
    ⎦
    -0.43
     aven
    -0.42
     crystall
    -0.41
    ValueStyle
    -0.41
     esté
    -0.40
    IAction
    -0.40
    usercontent
    -0.40
    ⟬
    -0.40
     kenn
    -0.39
    POSITIVE LOGITS
     Италијани
    0.49
     crawling
    0.49
    pping
    0.46
     '\\;'
    0.45
    hésite
    0.45
    ingly
    0.44
     crawls
    0.42
    WriteLiteral
    0.42
    craw
    0.42
    assies
    0.42
    Act Density 0.310%

    No Known Activations