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

    Neuronpedia

    INDEX
    Explanations

    state / variable declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.95
     CBD
    0.77
     in
    0.76
     [
    0.75
    ੀ
    0.75
     N
    0.74
    ्स
    0.73
     as
    0.72
     S
    0.71
    ों
    0.71
    POSITIVE LOGITS
     necesariamente
    0.87
    ListenAnd
    0.86
    Kemudian
    0.86
    жным
    0.85
     уважаемые
    0.83
    ленное
    0.82
    Assured
    0.82
    ynomial
    0.82
     необходимые
    0.82
    ೋಜನ
    0.82
    Act Density 0.069%

    No Known Activations