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

    Neuronpedia

    INDEX
    Explanations

    conjunctions and lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ูนย์
    0.21
    Ῥ
    0.20
    MiddleLine
    0.20
    .$,
    0.20
    Ბ
    0.19
     जलाश
    0.19
    广泛
    0.19
    locationY
    0.19
    <unused52>
    0.19
    操作系统
    0.19
    POSITIVE LOGITS
     and
    0.59
     आणि
    0.48
     और
    0.47
     và
    0.46
     ಮತ್ತು
    0.45
    and
    0.44
     અને
    0.42
     এবং
    0.42
     மற்றும்
    0.42
     и
    0.41
    Act Density 0.693%

    No Known Activations