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

    Neuronpedia

    INDEX
    Explanations

    dopamine, motivation, policy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    balls
    0.42
    ivariable
    0.38
    vay
    0.38
    يته
    0.38
     prima
    0.38
    ंडे
    0.38
    ندا
    0.37
    NonQuery
    0.36
    bians
    0.36
    Tk
    0.35
    POSITIVE LOGITS
     तिल
    0.39
     अपॉ
    0.39
     Carb
    0.38
     этап
    0.38
    datepicker
    0.38
    ギュア
    0.38
     amazed
    0.37
     lái
    0.37
     хрони
    0.37
     astonishment
    0.37
    Act Density 0.000%

    No Known Activations