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

    Neuronpedia

    INDEX
    Explanations

    years followed by closing parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     파일을
    0.65
     mieście
    0.59
    🥢
    0.55
     oynuyoruz
    0.55
     newMovie
    0.54
     সহরের
    0.54
    पाउंड
    0.54
    اداسی
    0.54
    Flicky
    0.53
    ുവരി
    0.53
    POSITIVE LOGITS
    ).
    0.86
    ;
    0.85
    );
    0.84
    .
    0.83
    s
    0.79
    ,
    0.76
     and
    0.70
    S
    0.68
    ↵
    0.68
    )
    0.68
    Act Density 0.007%

    No Known Activations