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

    Neuronpedia

    INDEX
    Explanations

    protons or aspirin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -
    1.76
    re
    1.30
    id
    1.28
    ori
    1.24
     μια
    1.23
    ir
    1.21
    ö
    1.21
    om
    1.20
    ang
    1.20
    or
    1.20
    POSITIVE LOGITS
    स्टोन
    1.55
    ۾
    1.45
    ाइन
    1.41
    たち
    1.30
    చ్చే
    1.30
    ()=>{
    1.29
    壹章
    1.29
    LIOGRAPHY
    1.27
    <unused69>
    1.26
    ১৪
    1.26
    Act Density 0.002%

    No Known Activations