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

    Neuronpedia

    INDEX
    Explanations

    proper nouns and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eseorang
    0.75
    Ꮬ
    0.73
    Компания
    0.72
    owneri
    0.71
    󰀄
    0.68
    <unused657>
    0.66
    ൭
    0.66
    ങ്ങാ
    0.65
    價格
    0.64
    glichkeiten
    0.64
    POSITIVE LOGITS
     S
    0.93
    S
    0.87
    .
    0.86
     E
    0.83
     H
    0.82
     L
    0.82
     B
    0.80
     N
    0.78
     G
    0.76
     maupun
    0.76
    Act Density 0.000%

    No Known Activations