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

    Neuronpedia

    INDEX
    Explanations

    code structures and common library names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     velocità
    0.90
     powerful
    0.87
     precious
    0.85
     př
    0.83
     payable
    0.82
     potenti
    0.78
     relentless
    0.78
     attent
    0.77
     logistics
    0.77
     shorter
    0.77
    POSITIVE LOGITS
    ların
    1.05
    paragus
    0.97
    */)
    0.95
     কালিক
    0.94
    entrée
    0.94
    डिएटली
    0.94
    AC
    0.93
    stos
    0.92
    妇
    0.92
    positive
    0.92
    Act Density 0.023%

    No Known Activations