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

    Neuronpedia

    INDEX
    Explanations

    specific formatting or symbols in text

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

    protein mutation notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    haltens
    -0.38
     îna
    -0.34
    자인
    -0.33
    SizeMode
    -0.32
     Ihr
    -0.32
     București
    -0.31
    #
    -0.31
     declarado
    -0.31
     hvad
    -0.30
     localizada
    -0.30
    POSITIVE LOGITS
     Administrativna
    0.70
    Datuak
    0.56
    SharedCtor
    0.56
     lenker
    0.55
    SharedDtor
    0.54
    ⟬
    0.54
    parsedMessage
    0.52
    Kolor
    0.51
    glEnd
    0.50
     EconPapers
    0.50
    Act Density 0.005%

    No Known Activations