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

    Neuronpedia

    INDEX
    Explanations

    believe in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    浣
    -0.08
    หลวง
    -0.08
    mpp
    -0.07
     المر
    -0.07
    每一个
    -0.07
    .react
    -0.07
    علامة
    -0.06
    .googleapis
    -0.06
    .ur
    -0.06
     degraded
    -0.06
    POSITIVE LOGITS
    0.07
    苞
    0.07
    _hide
    0.07
    -conscious
    0.07
    0.06
     sm
    0.06
    ед
    0.06
    0.06
    ني
    0.06
    0.06
    Act Density 0.007%

    No Known Activations