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

    Neuronpedia

    INDEX
    Explanations

    question text or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    하겠습니다
    0.42
    ступает
    0.42
    ాలని
    0.42
    enzione
    0.42
    ровала
    0.42
    하였다
    0.41
    हाला
    0.41
     বাঙালিদের
    0.40
    Scenario
    0.39
    шина
    0.39
    POSITIVE LOGITS
     processors
    0.46
     component
    0.39
     carriers
    0.39
     cells
    0.39
     المعروف
    0.38
     கருவ
    0.38
    饿
    0.38
     helpers
    0.37
     showcasing
    0.37
    QRCode
    0.37
    Act Density 0.000%

    No Known Activations