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

    Neuronpedia

    INDEX
    Explanations

    all followed by list items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MgII
    0.40
     Polarization
    0.39
    oflav
    0.38
    yscanner
    0.38
     GERM
    0.36
    ومن
    0.35
    IVO
    0.35
     регі
    0.35
     filtros
    0.34
    (
    0.34
    POSITIVE LOGITS
     đều
    0.49
     ovat
    0.48
     அனைத்தும்
    0.47
     są
    0.47
     tohoto
    0.47
     должны
    0.45
     действия
    0.45
    这一切
    0.45
     semuanya
    0.45
     ሁሉም
    0.44
    Act Density 0.024%

    No Known Activations