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

    Neuronpedia

    INDEX
    Explanations

    sentences that begin with "In" or "The"

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

    start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defaultstate
    -0.74
    Personensuche
    -0.67
    новништво
    -0.63
    PerformLayout
    -0.60
     Chwiliwch
    -0.59
    adaptiveStyles
    -0.58
    mergeFrom
    -0.56
    WriteBarrier
    -0.56
    最快更新
    -0.56
    antMatchers
    -0.55
    POSITIVE LOGITS
    <?
    0.36
    ótica
    0.34
    דות
    0.33
     bowiem
    0.33
    #![
    0.33
     educativa
    0.33
    Sometimes
    0.33
     Ocak
    0.32
     nahilalakip
    0.32
    I
    0.32
    Act Density 0.122%

    No Known Activations