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

    Neuronpedia

    INDEX
    Explanations

    programming overrides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िवा
    0.39
     Umbrella
    0.38
    umd
    0.36
    ozat
    0.36
    다
    0.36
     Padukone
    0.35
    льно
    0.35
     Alice
    0.35
     Motor
    0.35
     Rosa
    0.34
    POSITIVE LOGITS
     override
    0.70
     overridden
    0.69
    Override
    0.67
    override
    0.67
     overrides
    0.62
    Overrides
    0.56
     специфи
    0.55
     subclass
    0.54
     Override
    0.54
     getType
    0.54
    Act Density 0.005%

    No Known Activations