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

    Neuronpedia

    INDEX
    Explanations

    medical conditions

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

    medical conditions and diseases.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     from
    -1.35
    z
    -1.23
     at
    -1.13
    半天
    -1.10
     sekaligus
    -1.07
     erzeugt
    -1.05
     produziert
    -1.05
     geliefert
    -1.02
     shearing
    -1.02
    زمان
    -1.02
    POSITIVE LOGITS
     or
    1.62
    moderne
    1.45
     visuelle
    1.30
     kader
    1.27
     minimalis
    1.27
    mability
    1.22
     stadion
    1.20
     strukt
    1.20
     bakteri
    1.20
     materiaal
    1.20
    Act Density 0.060%

    No Known Activations