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

    Neuronpedia

    INDEX
    Explanations

    airport location and time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    é
    0.82
    I
    0.77
    ન
    0.75
    ون
    0.73
     وعلى
    0.71
    ю
    0.71
    ít
    0.69
    night
    0.69
     BufferedWriter
    0.68
    te
    0.67
    POSITIVE LOGITS
    urium
    0.90
    ും
    0.88
    ாத
    0.88
    を確認
    0.87
    πως
    0.85
     Vanity
    0.82
    vection
    0.82
    லாமல்
    0.82
     senseless
    0.80
     bruta
    0.79
    Act Density 0.001%

    No Known Activations