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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     कह
    -0.08
    stractions
    -0.07
    weeney
    -0.06
    策
    -0.06
     сух
    -0.06
    �자
    -0.06
    acimiento
    -0.06
    .bank
    -0.06
    ülü
    -0.06
     bazı
    -0.06
    POSITIVE LOGITS
     Aussie
    0.07
    >();
↵
↵
    0.06
     Peace
    0.06
     ')↵
    0.06
     \↵↵
    0.06
    [port
    0.06
    �
    0.06
    (inflater
    0.06
    :'
    0.06
     Essay
    0.06
    Act Density 0.038%

    No Known Activations