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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    组图
    -0.07
    ﳊ
    -0.07
    onestly
    -0.07
    进项
    -0.07
    Ȥ
    -0.07
     liqu
    -0.07
     './../
    -0.07
    𝜃
    -0.07
    _datasets
    -0.07
    POSITIVE LOGITS
    樣
    0.07
    efe
    0.06
     claim
    0.06
    _now
    0.06
    .focus
    0.06
    kich
    0.06
    قبول
    0.06
    莱
    0.06
    <center
    0.06
    ⓘ
    0.06
    Act Density 0.072%

    No Known Activations