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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_acts-logits-general · gemini-2.5-flash-lite

    of a or the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ä
    0.61
    ą
    0.50
    '
    0.47
    äne
    0.46
    uan
    0.45
    ę
    0.45
     från
    0.42
     bằng
    0.42
    íte
    0.42
     από
    0.41
    POSITIVE LOGITS
    ר
    0.55
    the
    0.43
     endangering
    0.41
    THE
    0.40
    ו
    0.39
    ar
    0.38
     বসবাসের
    0.38
    FAILURE
    0.37
    وين
    0.37
     Camus
    0.37
    Act Density 6.807%

    No Known Activations