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

    Neuronpedia

    INDEX
    Explanations

    me know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     various
    0.54
     Gaussian
    0.52
    \
    0.52
     כאשר
    0.51
     An
    0.50
     luminance
    0.49
     использу
    0.49
     verwendet
    0.49
    (
    0.49
     sequential
    0.49
    POSITIVE LOGITS
    empê
    0.67
    éviter
    0.61
    ayad
    0.60
     Wikiseite
    0.58
    ătă
    0.58
    ွ
    0.58
    ᅨ
    0.57
    inguém
    0.57
    untut
    0.57
    ក់
    0.57
    Act Density 4.540%

    No Known Activations