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

    Neuronpedia

    INDEX
    Explanations

    URLs or links to online resources

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

    web addresses and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    </b>
    -0.36
    </strong>
    -0.34
    op
    -0.30
    </i>
    -0.30
    </u>
    -0.28
    </h3>
    -0.28
    argb
    -0.27
     solde
    -0.27
    f
    -0.26
    </h2>
    -0.26
    POSITIVE LOGITS
    Personendaten
    0.80
    tagHelperRunner
    0.80
     disambiguazione
    0.79
     <<<<<<<<<<<<<<
    0.78
     autorytatywna
    0.75
    Personensuche
    0.74
    BeginContext
    0.71
     myſelf
    0.71
    évaluateur
    0.70
     ProtoMessage
    0.70
    Act Density 0.449%

    No Known Activations