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

    Neuronpedia

    INDEX
    Explanations

    exertion and strain on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۳
    0.92
    3
    0.81
    0
    0.71
    battery
    0.71
    서
    0.70
     Calm
    0.70
    description
    0.69
     Baja
    0.68
    ${
    0.68
     to
    0.67
    POSITIVE LOGITS
    ن
    0.84
    я
    0.76
    on
    0.75
    ار
    0.70
     exertion
    0.68
    数百
    0.68
    हरु
    0.66
     nabí
    0.65
    ก
    0.63
     entraîne
    0.62
    Act Density 0.007%

    No Known Activations