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

    Neuronpedia

    INDEX
    Explanations

    forward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cardinals
    -0.08
     Performance
    -0.07
     Ops
    -0.07
     ministers
    -0.07
     rivals
    -0.07
    中枢
    -0.07
     DEV
    -0.07
     Merc
    -0.07
    生病
    -0.07
    삮
    -0.07
    POSITIVE LOGITS
    ا�
    0.07
    казан
    0.07
     Tatto
    0.07
     expose
    0.07
     directed
    0.07
    主办方
    0.07
    があ
    0.07
    acking
    0.06
    stitución
    0.06
    _UNITS
    0.06
    Act Density 0.002%

    No Known Activations