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

    Neuronpedia

    INDEX
    Explanations

    class, type, struct, inject, function, Rosa, blend

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    )。
    0.64
    )，
    0.61
     спасибо
    0.58
    );
    0.52
     et
    0.51
    的其他
    0.50
    )`,
    0.50
     urna
    0.49
    還可以
    0.49
    )*
    0.48
    POSITIVE LOGITS
    scheduled
    0.51
    }+\
    0.49
    Logistic
    0.48
    im
    0.48
    optical
    0.46
    ativ
    0.46
    avkh
    0.46
    authors
    0.46
    mh
    0.45
    ه‌ی
    0.45
    Act Density 0.000%

    No Known Activations