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

    Neuronpedia

    INDEX
    Explanations

    AI Models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ne
    0.92
    d
    0.89
    av
    0.88
    v
    0.87
    l
    0.85
    at
    0.85
    k
    0.81
    n
    0.81
    w
    0.80
    е
    0.80
    POSITIVE LOGITS
     hinges
    0.90
    をはじめ
    0.77
     deployed
    0.74
    ০
    0.74
    ダム
    0.73
     خوان
    0.71
    ເລ
    0.71
     châu
    0.71
    грамма
    0.70
     bestätigt
    0.70
    Act Density 0.001%

    No Known Activations