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

    Neuronpedia

    INDEX
    Explanations

    cannot avoid or resist

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    crew
    0.96
    veel
    0.95
     warms
    0.92
    ideal
    0.86
     warmly
    0.86
     warto
    0.86
     பெற்று
    0.84
     warmed
    0.83
    Warm
    0.82
     Ideal
    0.82
    POSITIVE LOGITS
     inescap
    1.15
     unavoid
    0.99
     inevitably
    0.97
     Cannot
    0.97
     mandate
    0.94
     compulsory
    0.92
     невозможно
    0.92
    Cannot
    0.92
     cannot
    0.91
    oirs
    0.89
    Act Density 0.042%

    No Known Activations