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

    Neuronpedia

    INDEX
    Explanations

    code structure and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    otechnology
    0.30
     particularmente
    0.28
     intravenously
    0.28
    osexuality
    0.27
    particularly
    0.27
    Newly
    0.27
    getNumberOf
    0.26
    ‌
    0.25
    PERATURE
    0.25
    らかじめ
    0.25
    POSITIVE LOGITS
     iff
    0.31
     dunno
    0.29
     explode
    0.29
     इनको
    0.28
     ogn
    0.27
     Lookup
    0.27
     idk
    0.27
     outro
    0.27
     confound
    0.26
     %>%
    0.26
    Act Density 0.146%

    No Known Activations