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

    Neuronpedia

    INDEX
    Explanations

    day of employment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    u
    1.83
     змо
    1.57
    ются
    1.55
    وْ
    1.53
    ulfill
    1.53
    多い
    1.52
    ITY
    1.49
     exercitation
    1.46
    ुसार
    1.46
     irreducible
    1.45
    POSITIVE LOGITS
     ऑफ
    1.80
    Unter
    1.79
     amikor
    1.76
     Recession
    1.70
     oef
    1.66
    RELATED
    1.63
    рам
    1.63
    dimethyl
    1.63
    1.62
    ruction
    1.62
    Act Density 0.009%

    No Known Activations