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

    Neuronpedia

    INDEX
    Explanations

    effective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    真正
    -0.07
    回来
    -0.07
     Crazy
    -0.07
     Eugene
    -0.07
    RequestParam
    -0.07
    为什么
    -0.06
     dome
    -0.06
     Spike
    -0.06
     усе
    -0.06
     mẫu
    -0.06
    POSITIVE LOGITS
    (es
    0.07
    (stderr
    0.07
    ême
    0.06
     %}↵
    0.06
     datap
    0.06
    getActiveSheet
    0.06
     ihtiyaç
    0.06
     Plaint
    0.06
    _fill
    0.06
    "';
    0.06
    Act Density 0.000%

    No Known Activations