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

    Neuronpedia

    INDEX
    Explanations

    mathematical or computational expressions involving variables and calculations

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

    Code or calculations including multiplication/division

    np_acts-logits-general · gemini-2.0-flash

    division operations with numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     away
    -0.48
    ber
    -0.46
    âme
    -0.44
     Drei
    -0.44
     Topf
    -0.44
    PointerException
    -0.43
     tantum
    -0.42
    趕
    -0.42
     Fair
    -0.42
    Fair
    -0.41
    POSITIVE LOGITS
    Lähteet
    0.86
     nahilalakip
    0.80
    Enllaces
    0.76
     GenerationType
    0.75
     surla
    0.74
    Personendaten
    0.72
    CppMethod
    0.69
     disponibilités
    0.68
    ChildScrollView
    0.66
    expandindo
    0.66
    Act Density 0.253%

    No Known Activations