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

    Neuronpedia

    INDEX
    Explanations

    function definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いても
    -1.02
     without
    -0.94
    middle
    -0.93
    чиков
    -0.91
     gjø
    -0.89
    without
    -0.89
     Recovery
    -0.89
    Recovery
    -0.89
    resizeMode
    -0.88
    hibits
    -0.87
    POSITIVE LOGITS
    ễm
    0.95
     тоже
    0.88
    為に
    0.87
     wundersch
    0.85
     такая
    0.83
    Ogni
    0.82
    反思
    0.81
     jemals
    0.81
     пище
    0.81
     you
    0.81
    Act Density 0.001%

    No Known Activations