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

    Neuronpedia

    INDEX
    Explanations

    explanation of text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.84
     -
    0.64
     -,
    0.57
    chutz
    0.57
    scribed
    0.56
    锵
    0.55
    même
    0.55
     +
    0.54
    ázquez
    0.54
    μών
    0.54
    POSITIVE LOGITS
    u
    0.64
     WERE
    0.64
    ו
    0.62
    ز
    0.61
     NEET
    0.60
     OXIDES
    0.58
     yana
    0.57
     clout
    0.57
    క్‌
    0.57
    نے
    0.57
    Act Density 0.000%

    No Known Activations