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

    Neuronpedia

    INDEX
    Explanations

    how things started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     restricting
    0.46
     undertake
    0.45
     соблю
    0.44
     પ્રય
    0.43
     suggest
    0.42
    över
    0.42
     प्रयत्न
    0.41
    CopyWith
    0.41
    writing
    0.40
     засто
    0.40
    POSITIVE LOGITS
     americanos
    0.46
     eles
    0.45
     rumores
    0.44
    ’
    0.44
     americano
    0.43
     mexicana
    0.43
     inú
    0.43
    联网
    0.43
    ட்கள்
    0.43
     stagione
    0.42
    Act Density 0.006%

    No Known Activations