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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obtains
    -0.07
    टक
    -0.07
    _FAULT
    -0.07
    compat
    -0.07
    测试
    -0.07
    ofil
    -0.07
    battle
    -0.07
     �
    -0.07
     тв
    -0.06
    ่วย
    -0.06
    POSITIVE LOGITS
     McKenzie
    0.07
     specificity
    0.06
     모든
    0.06
     liền
    0.06
    fer
    0.06
    uencia
    0.06
     Manufacturer
    0.06
     джер
    0.06
    931
    0.06
     zeigt
    0.06
    Act Density 0.002%

    No Known Activations