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

    Neuronpedia

    INDEX
    Explanations

    programming and configuration language elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     פֿ
    -0.75
     Sixteenth
    -0.72
    ('../
    -0.71
    todos
    -0.71
    octave
    -0.70
    FORCEMENT
    -0.69
     Один
    -0.68
    BarButtonItem
    -0.68
     promet
    -0.68
    PRESS
    -0.67
    POSITIVE LOGITS
     vänner
    0.73
     expliquer
    0.70
     Referee
    0.69
    mutual
    0.65
    statics
    0.65
    Matéri
    0.62
     rodillas
    0.61
    TCS
    0.61
    kta
    0.61
     تلك
    0.61
    Act Density 0.058%

    No Known Activations