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

    Neuronpedia

    INDEX
    Explanations

    numerical values representing data points or parameters in mathematical or programming contexts

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

    mathematical expressions with exponents

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.84
    AccessorTable
    -0.56
    HtmlAttribute
    -0.52
    IntoConstraints
    -0.50
    AutoScaleMode
    -0.49
    StoreMessageInfo
    -0.49
    AsUp
    -0.49
     betweenstory
    -0.48
    цездатний
    -0.47
     виправивши
    -0.47
    POSITIVE LOGITS
    PRNewswire
    0.49
    awaiter
    0.36
     thụ
    0.36
     discriminant
    0.35
    cosine
    0.35
    writeString
    0.34
    URBANA
    0.34
     SUDOC
    0.34
    glGen
    0.34
    strij
    0.33
    Act Density 0.121%

    No Known Activations