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

    Neuronpedia

    INDEX
    Explanations

    ability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Headphones
    1.01
    fry
    0.99
    巖
    0.98
    slug
    0.96
    schaft
    0.96
    shots
    0.94
    sru
    0.94
    removing
    0.94
    fried
    0.93
    storms
    0.93
    POSITIVE LOGITS
    т
    1.16
     runde
    1.07
    те
    1.06
    л
    1.05
     afecta
    1.00
    uck
    0.96
    ння
    0.95
    zzle
    0.95
    鸪
    0.93
    کا
    0.93
    Act Density 0.193%

    No Known Activations