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

    Neuronpedia

    INDEX
    Explanations

    references to academic publications and their characteristics

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

    volume, Vol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.49
     miniaturka
    -0.48
    ConstraintMaker
    -0.47
     rahasia
    -0.47
     ModelRenderer
    -0.46
    uxxxx
    -0.45
    ersatz
    -0.44
    ----</
    -0.44
     secretos
    -0.43
     tamen
    -0.40
    POSITIVE LOGITS
     الحره
    0.50
    MarshalTo
    0.42
     CreateTagHelper
    0.40
    Халык
    0.40
    исленность
    0.36
    nesc
    0.36
    Diweddarwch
    0.35
    UseVisualStyle
    0.35
    specialchars
    0.35
     चीज़ों
    0.35
    Act Density 0.010%

    No Known Activations