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

    Neuronpedia

    INDEX
    Explanations

    url prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     []),
    0.39
    BUND
    0.38
     sla
    0.38
     Palin
    0.38
    PV
    0.37
    ),
    0.37
    VIII
    0.37
    esta
    0.37
    هدف
    0.36
    actos
    0.36
    POSITIVE LOGITS
     hype
    0.38
    Holding
    0.36
     फिट
    0.35
     cozy
    0.35
    ★★
    0.35
     дер
    0.33
     प्राइम
    0.33
    UTCDate
    0.32
     ফে
    0.32
     Дер
    0.32
    Act Density 0.000%

    No Known Activations