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

    Neuronpedia

    INDEX
    Explanations

    building relationships

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Calendar
    -0.08
    CBD
    -0.08
     included
    -0.07
    一般
    -0.07
    ющ
    -0.07
     CBD
    -0.07
    атора
    -0.07
     معرفی
    -0.07
     Michael
    -0.06
    erging
    -0.06
    POSITIVE LOGITS
     जग
    0.06
     ис
    0.06
     Sở
    0.06
    调查
    0.06
     Succ
    0.06
    ประม
    0.05
    _trees
    0.05
    -me
    0.05
     ime
    0.05
     Supported
    0.05
    Act Density 0.021%

    No Known Activations