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

    Neuronpedia

    INDEX
    Explanations

    risk and event

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     précision
    0.67
     courbes
    0.66
     leitura
    0.64
     mengajak
    0.64
    もう少し
    0.63
     desiderio
    0.63
     ótimo
    0.63
    差异
    0.62
     birkaç
    0.62
    少なくとも
    0.62
    POSITIVE LOGITS
     comply
    0.78
     endure
    0.67
     pay
    0.65
     succumb
    0.64
     relinquish
    0.63
     choose
    0.63
     acquies
    0.62
     cooperate
    0.62
     compromised
    0.62
     forfe
    0.62
    Act Density 0.000%

    No Known Activations