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

    Neuronpedia

    INDEX
    Explanations

    mathematical or code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    લ
    0.97
     bambini
    0.90
    ار
    0.85
    ле
    0.83
    ם
    0.80
     febbraio
    0.80
     paylaş
    0.80
    ր
    0.80
    ന്യൂ
    0.80
    ра
    0.79
    POSITIVE LOGITS
     estuaries
    0.68
     compounds
    0.65
    n
    0.65
     nucle
    0.64
     :
    0.64
     decisions
    0.63
     factors
    0.63
     k
    0.63
     nuk
    0.63
     isomers
    0.63
    Act Density 0.001%

    No Known Activations