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

    Neuronpedia

    INDEX
    Explanations

    /* comment or placeholder for color or id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ный
    1.74
     dotyczą
    1.60
     এজন্য
    1.54
    expr
    1.48
    week
    1.47
    uring
    1.47
    пка
    1.47
    ни
    1.46
    و
    1.42
    ite
    1.41
    POSITIVE LOGITS
    ים
    2.00
    بوع
    2.00
    sb
    1.97
    sales
    1.96
     lc
    1.94
    sá
    1.92
    sız
    1.86
     lcm
    1.85
    სი
    1.84
     acl
    1.82
    Act Density 0.043%

    No Known Activations