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

    Neuronpedia

    INDEX
    Explanations

    affirmative expressions or confirmations

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

    affirmation and agreement

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⓧ
    -0.39
    Quint
    -0.35
    fromCharCode
    -0.35
    //
    -0.34
     Colon
    -0.33
     Ext
    -0.32
     transfieras
    -0.32
     requ
    -0.31
     بيها
    -0.31
     gev
    -0.31
    POSITIVE LOGITS
     Grüsse
    0.59
     defStyleAttr
    0.59
    writeFieldEnd
    0.55
    CROSSTALK
    0.53
    tagHelper
    0.53
     Bewußt
    0.52
     zimowa
    0.52
    enderror
    0.52
     ModelRenderer
    0.52
    makeText
    0.51
    Act Density 0.020%

    No Known Activations