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

    Neuronpedia

    INDEX
    Explanations

    strong feelings or certainty

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     disputes
    0.78
     hakkında
    0.76
    改
    0.76
     仕様
    0.74
    পের
    0.73
     বর্তমানে
    0.72
     ympä
    0.71
    調べて
    0.71
     الملابس
    0.71
     interessiert
    0.70
    POSITIVE LOGITS
     pernicious
    1.04
     heady
    0.93
     insidious
    0.93
     shameless
    0.90
     inescap
    0.89
     sobering
    0.89
     cosmic
    0.85
     visceral
    0.84
     corollary
    0.83
     irresist
    0.82
    Act Density 0.323%

    No Known Activations