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

    Neuronpedia

    INDEX
    Explanations

    hexadecimal strings and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    用到
    0.92
    质量
    0.81
     Cuenta
    0.81
    Ư
    0.80
    Escol
    0.79
     Bảo
    0.78
    ियाँ
    0.78
    گری
    0.78
     Fahrt
    0.77
    Callback
    0.76
    POSITIVE LOGITS
     glory
    0.82
     seo
    0.79
     Luxemburg
    0.79
     PSI
    0.74
     bodies
    0.74
     imp
    0.73
     indoctr
    0.73
     latina
    0.73
     oj
    0.72
     bracket
    0.72
    Act Density 0.018%

    No Known Activations