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

    Neuronpedia

    INDEX
    Explanations

    not cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ധിപ
    0.44
    ")):
    0.43
    ScienceStudent
    0.40
     Bericht
    0.39
     berichten
    0.39
    ophytes
    0.38
     Drummond
    0.38
    itelist
    0.37
    %;">
    0.37
    _{\|
    0.37
    POSITIVE LOGITS
    कै
    0.47
    надца
    0.46
    į
    0.45
     stylish
    0.44
     birbirinden
    0.44
    कल
    0.43
    UCI
    0.43
     fluttering
    0.43
     perusahaan
    0.42
     kurang
    0.42
    Act Density 0.000%

    No Known Activations