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

    Neuronpedia

    INDEX
    Explanations

    disclaimers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    |[
    -0.07
     Expedition
    -0.06
     Sony
    -0.06
    Creates
    -0.06
    _switch
    -0.06
    _gain
    -0.06
    爭
    -0.06
    اگر
    -0.06
     वस
    -0.06
     _(
    -0.06
    POSITIVE LOGITS
    ("/")↵
    0.07
    онд
    0.07
     Kv
    0.06
     Bundes
    0.06
    xe
    0.06
     Під
    0.06
     bunun
    0.06
    _ASCII
    0.06
     зрения
    0.06
    ;',↵
    0.06
    Act Density 0.012%

    No Known Activations