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

    Neuronpedia

    INDEX
    Explanations

    converting formats or units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ombra
    0.44
     colocadas
    0.43
    erness
    0.40
     awakens
    0.40
     nächsten
    0.40
     आरोप
    0.39
    onResume
    0.39
    力量
    0.38
    pits
    0.38
     consciência
    0.38
    POSITIVE LOGITS
     converting
    1.18
     Converting
    1.16
     convert
    1.06
     Converts
    1.05
    Converting
    1.05
     convertir
    1.03
     Convert
    1.02
    Convert
    1.00
     converts
    1.00
    converting
    0.99
    Act Density 0.196%

    No Known Activations