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

    Neuronpedia

    INDEX
    Explanations

    code blocks `{}`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ңа
    0.77
     exemplified
    0.73
    रो
    0.72
    लाई
    0.72
    オ
    0.71
    ной
    0.70
    𝗁
    0.70
     Peptide
    0.68
    ⟧
    0.68
    гө
    0.67
    POSITIVE LOGITS
    ut
    0.77
     kontak
    0.76
     perjalanan
    0.76
     Kontak
    0.76
     trak
    0.76
    ע
    0.75
     votos
    0.75
    ﾞ
    0.73
    ruta
    0.73
     восем
    0.73
    Act Density 0.011%

    No Known Activations