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

    Neuronpedia

    INDEX
    Explanations

    names following locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝑆
    0.50
     ಉತ್ಪನ್ನ
    0.47
    쌤
    0.47
     있던
    0.46
    switcher
    0.45
    腎
    0.44
    ಪ್ಪ
    0.43
     EGFR
    0.43
     SPSS
    0.42
     CBT
    0.42
    POSITIVE LOGITS
    ));
    0.54
    ,
    0.51
     disk
    0.47
    InnoDB
    0.46
     роках
    0.45
     bah
    0.42
    Callories
    0.42
    haya
    0.42
    Disk
    0.42
    اندار
    0.42
    Act Density 0.003%

    No Known Activations