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

    Neuronpedia

    INDEX
    Explanations

    first appearance or occurrence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    étaient
    1.16
     извест
    1.16
    咘
    1.15
     চিকিত
    1.12
    𝕌
    1.11
    ﺍ
    1.10
    的基础上
    1.09
     consciência
    1.09
    которы
    1.07
    ته
    1.05
    POSITIVE LOGITS
    sam
    1.30
    1
    1.19
    screens
    1.17
    san
    1.12
    signs
    1.10
    g
    1.10
    3
    1.09
    sounds
    1.08
    f
    1.06
    j
    1.06
    Act Density 0.000%

    No Known Activations