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

    Neuronpedia

    INDEX
    Explanations

    quant

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bí
    -0.08
     Vest
    -0.07
     muster
    -0.07
     constituents
    -0.07
     makeup
    -0.06
     stimulus
    -0.06
    ײ
    -0.06
    )Math
    -0.06
    BufferSize
    -0.06
    lage
    -0.06
    POSITIVE LOGITS
    -thread
    0.08
     getTotal
    0.08
     colonial
    0.07
     wrap
    0.07
    我个人
    0.07
    物理学
    0.07
     Own
    0.07
    PEED
    0.07
    实惠
    0.07
    时光
    0.07
    Act Density 0.005%

    No Known Activations