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

    Neuronpedia

    INDEX
    Explanations

    XML tag endings or attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    1.05
     C
    0.99
     T
    0.93
     E
    0.92
     H
    0.89
    ↵↵
    0.87
     (**
    0.86
     e
    0.79
     С
    0.79
    T
    0.79
    POSITIVE LOGITS
    Cantidad
    0.91
    Ral
    0.91
     পরবর্তী
    0.84
    期限
    0.84
    很大
    0.82
    ات
    0.79
    Saldo
    0.76
    RELATIVA
    0.75
    转变
    0.75
    IPP
    0.74
    Act Density 0.541%

    No Known Activations