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

    Neuronpedia

    INDEX
    Explanations

    models, butter, fire, vs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    size
    0.45
    tuple
    0.42
    sgem
    0.42
    scope
    0.41
     zetten
    0.41
    DAR
    0.40
     भेजे
    0.40
    <unused9>
    0.40
    mathcal
    0.39
    rte
    0.39
    POSITIVE LOGITS
    lüğü
    0.44
    ho
    0.42
    TestMethod
    0.41
    èo
    0.41
     קר
    0.41
    хо
    0.41
     самую
    0.41
     автора
    0.40
     полного
    0.40
    adien
    0.40
    Act Density 0.001%

    No Known Activations