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

    Neuronpedia

    INDEX
    Explanations

    Gorges Dam, Upper Egypt, durum wheat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     carburetor
    0.76
    $
    0.70
    エア
    0.64
     harmonies
    0.62
     frogs
    0.61
     crevices
    0.61
     amplifier
    0.60
    емой
    0.60
    0.59
     lilies
    0.59
    POSITIVE LOGITS
    daki
    0.89
    n
    0.83
    н
    0.80
     The
    0.80
     Мне
    0.78
    name
    0.77
    ထဲ
    0.76
    string
    0.76
    prediction
    0.75
     Архивная
    0.75
    Act Density 0.001%

    No Known Activations