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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pleading
    -0.07
    民政
    -0.06
     תה
    -0.06
     сами
    -0.06
    ABCDEFGHIJKLMNOPQRSTUVWXYZ
    -0.06
     Colorado
    -0.06
    Senha
    -0.06
    采摘
    -0.06
    契合
    -0.06
    _sem
    -0.06
    POSITIVE LOGITS
     theater
    0.08
    lp
    0.07
    startdate
    0.07
     AW
    0.07
    rr
    0.06
    ┏
    0.06
     chain
    0.06
    掌
    0.06
    速度
    0.06
     endwhile
    0.06
    Act Density 0.002%

    No Known Activations