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

    Neuronpedia

    INDEX
    Explanations

    weight in lbs and pounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     D
    0.67
    D
    0.61
    L
    0.57
    U
    0.54
    Dru
    0.53
     Veja
    0.52
    I
    0.51
    ﺪ
    0.50
    Lib
    0.49
    ORA
    0.48
    POSITIVE LOGITS
     місце
    0.59
    સભા
    0.59
     athletes
    0.58
     asker
    0.57
     buzzer
    0.55
     máte
    0.55
     athlete
    0.54
     pioneers
    0.54
     paramedics
    0.54
    гій
    0.54
    Act Density 0.001%

    No Known Activations