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

    Neuronpedia

    INDEX
    Explanations

    lying, lied, lie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     OST
    0.55
    Ost
    0.45
    OST
    0.45
    colare
    0.43
     Ost
    0.39
     γρα
    0.39
    Describes
    0.39
    展现
    0.38
     ETC
    0.38
    ставка
    0.38
    POSITIVE LOGITS
    utenants
    0.85
     lying
    0.72
     lies
    0.71
     lie
    0.70
     LIE
    0.69
     lied
    0.68
     Lie
    0.66
    Lie
    0.61
     Lies
    0.59
    utenant
    0.58
    Act Density 0.005%

    No Known Activations