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

    Neuronpedia

    INDEX
    Explanations

    credit, card, run, key

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    0.49
    /
    0.40
    .
    0.34
    ー
    0.33
     của
    0.32
    ↵
    0.32
    +
    0.31
    es
    0.30
    н
    0.29
    ;
    0.29
    POSITIVE LOGITS
     Housewives
    0.29
     Menschen
    0.27
     Bayesian
    0.27
    危险
    0.27
     பொருளாதார
    0.27
     नाखून
    0.26
    વાહી
    0.26
     اید
    0.26
    流动
    0.26
    异步
    0.26
    Act Density 0.291%

    No Known Activations