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

    Neuronpedia

    INDEX
    Explanations

    job description or posting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ма
    1.86
    orical
    1.73
    ributions
    1.69
                    
    1.68
    ));
    1.62
    us
    1.61
    prises
    1.60
    ace
    1.59
    ))
    1.58
    quent
    1.55
    POSITIVE LOGITS
    ่า
    2.44
    ו
    2.33
    יל
    2.28
    ৪
    2.19
    में
    2.13
    یس
    2.08
    ون
    2.03
    ای
    2.03
    و
    2.03
    ל
    2.02
    Act Density 0.018%

    No Known Activations