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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Sai
    0.78
    sai
    0.75
    MCA
    0.74
    Sai
    0.71
    SAP
    0.69
     SAP
    0.69
     sai
    0.68
    مج
    0.67
     SAI
    0.65
    ۵
    0.62
    POSITIVE LOGITS
    kannt
    0.85
    反應
    0.84
    ilyn
    0.82
     अड्
    0.81
    sommets
    0.81
    udem
    0.81
     restraint
    0.80
     красоты
    0.80
     विद्यार्थ्या
    0.79
     домаћинстава
    0.79
    Act Density 0.003%

    No Known Activations