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

    Neuronpedia

    INDEX
    Explanations

    mentions of significant numbers or statistics

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

    names of people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CascadeType
    -0.53
     BorderSide
    -0.53
    ]")]
    -0.48
    __*/
    -0.47
    #
    -0.43
    WindowConstants
    -0.41
    Sinopse
    -0.41
    meisterschaften
    -0.41
    ご紹介
    -0.40
    iettivo
    -0.40
    POSITIVE LOGITS
    AccessorTable
    0.52
     EconPapers
    0.51
     defaultstate
    0.44
    AndEndTag
    0.43
    celotti
    0.41
     assinatura
    0.40
    InitVars
    0.40
     Rotating
    0.40
     praising
    0.38
    pulumi
    0.38
    Act Density 0.004%

    No Known Activations