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

    Neuronpedia

    INDEX
    Explanations

    I statements and personal opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     (
    0.34
     garments
    0.32
    -
    0.30
    (
    0.29
     authentication
    0.29
     length
    0.29
     sequences
    0.29
     restraints
    0.28
     cryptographic
    0.28
     concatenation
    0.27
    POSITIVE LOGITS
     Бушлай
    0.32
     казіно
    0.31
     gustaría
    0.28
     giovani
    0.28
     acredito
    0.28
    觉得
    0.27
     थिंक
    0.27
     पेशे
    0.27
     prawie
    0.27
    觉得自己
    0.27
    Act Density 0.798%

    No Known Activations