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

    Neuronpedia

    INDEX
    Explanations

    phrases that include the word "for."

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

    purpose or reason

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gu
    -0.49
    gad
    -0.44
    Novel
    -0.42
     risult
    -0.42
    ambo
    -0.42
     présentant
    -0.42
     Ketten
    -0.41
     sereia
    -0.41
     wyst
    -0.41
    Nov
    -0.41
    POSITIVE LOGITS
     purpoſe
    0.54
    IsMutable
    0.54
    ⟬
    0.51
     Voulez
    0.46
     ComVisible
    0.46
    @[+][
    0.46
     AspNetCore
    0.45
     ModelExpression
    0.44
    yntaxException
    0.42
     pleaſure
    0.42
    Act Density 0.012%

    No Known Activations