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

    Neuronpedia

    INDEX
    Explanations

    presented legal arguments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    的核心
    -0.07
    們
    -0.07
    看电影
    -0.07
    spy
    -0.07
    峒
    -0.06
     Employee
    -0.06
    plode
    -0.06
    🛶
    -0.06
    氘
    -0.06
    ⁍
    -0.06
    POSITIVE LOGITS
     BEFORE
    0.07
     Tit
    0.07
     Sam
    0.07
    九大精神
    0.07
     spirit
    0.07
     Illustrated
    0.07
    spirit
    0.06
    _managed
    0.06
    面积
    0.06
     States
    0.06
    Act Density 0.000%

    No Known Activations