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

    Neuronpedia

    INDEX
    Explanations

    modification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    台湾
    -0.07
    港
    -0.07
     TICK
    -0.07
    阶段
    -0.07
     Turnbull
    -0.07
     Simone
    -0.07
    unn
    -0.07
    ritt
    -0.07
    穙
    -0.06
    赳
    -0.06
    POSITIVE LOGITS
     perceive
    0.07
     disrespect
    0.07
    (kind
    0.07
    可以使
    0.07
     blowing
    0.07
     Cooling
    0.07
     favorable
    0.07
    .shape
    0.07
    起到了
    0.07
    _fs
    0.07
    Act Density 0.008%

    No Known Activations