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

    Neuronpedia

    INDEX
    Explanations

    device version and unpredictability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     видимо
    0.41
    Чем
    0.40
    🕗
    0.39
     Cramer
    0.39
     coca
    0.38
     algorithms
    0.38
     ο
    0.37
     Coca
    0.37
     remorse
    0.37
    🐮
    0.37
    POSITIVE LOGITS
    jos
    0.46
    jo
    0.42
    piece
    0.40
    pared
    0.39
    kkue
    0.38
    mart
    0.37
    clients
    0.37
    joon
    0.37
    mod
    0.37
    sendPluginResult
    0.37
    Act Density 0.000%

    No Known Activations