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

    Neuronpedia

    INDEX
    Explanations

    specific product specifications and compatibility information

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

    Series of digits

    np_acts-logits-general · gemini-2.0-flash

    model modelmodel numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.84
    RectangleBorder
    -0.76
    InjectAttribute
    -0.74
     >=",
    -0.72
     ویکی‌پدیا
    -0.69
    ThroughAttribute
    -0.69
    GraphicsUnit
    -0.67
    ArgsConstructor
    -0.67
    ]")]
    -0.67
    ClientSize
    -0.65
    POSITIVE LOGITS
    B
    0.55
     Shakspeare
    0.52
    A
    0.51
     series
    0.51
    C
    0.51
    P
    0.48
    E
    0.47
    D
    0.46
    b
    0.46
    R
    0.44
    Act Density 0.328%

    No Known Activations