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

    Neuronpedia

    INDEX
    Explanations

    functional programming concepts and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    er
    0.60
     Responses
    0.44
    Path
    0.43
    komm
    0.43
    Words
    0.42
     Bib
    0.42
    e
    0.42
    y
    0.42
    to
    0.42
    jud
    0.42
    POSITIVE LOGITS
     oreille
    0.45
     glaring
    0.43
     injure
    0.43
     pel
    0.42
     концер
    0.40
     nhẹ
    0.40
     záb
    0.40
    |[
    0.40
     cinquième
    0.40
     neque
    0.39
    Act Density 0.001%

    No Known Activations