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

    Neuronpedia

    INDEX
    Explanations

    names, prices, characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    da
    1.04
    र
    0.89
    de
    0.88
    th
    0.84
    "
    0.83
    ds
    0.80
    cm
    0.78
    er
    0.77
    m
    0.77
    م
    0.77
    POSITIVE LOGITS
     navegador
    1.09
     legales
    1.08
     nở
    1.08
     locais
    1.05
     variável
    1.05
     sinner
    1.05
     variáveis
    1.00
     redshifts
    1.00
     saudável
    1.00
     andar
    1.00
    Act Density 0.001%

    No Known Activations