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

    Neuronpedia

    INDEX
    Explanations

    testosterone, snow, Lifetime access, cords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     звук
    0.54
    Flicky
    0.52
    唦
    0.51
     presets
    0.50
    الحضور
    0.49
    spannung
    0.49
     برش
    0.48
     accelerate
    0.48
     เสียง
    0.48
    搡
    0.48
    POSITIVE LOGITS
    C
    0.52
    is
    0.51
    chil
    0.44
    id
    0.43
     inne
    0.43
     (
    0.42
    L
    0.42
    RA
    0.42
    0.42
    lard
    0.41
    Act Density 0.000%

    No Known Activations