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

    Neuronpedia

    INDEX
    Explanations

    historical periods, cultures, and styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     facilitating
    0.40
     thermodynam
    0.40
     inroads
    0.39
     enables
    0.37
     applies
    0.37
     merits
    0.36
     determines
    0.36
     lags
    0.35
     constitutes
    0.35
     but
    0.35
    POSITIVE LOGITS
     erau
    0.42
    风格
    0.41
     스타일
    0.40
    Illustrated
    0.38
     стиле
    0.37
    诗
    0.37
     стоковое
    0.37
    המ
    0.37
     apothecary
    0.37
    󠁳
    0.37
    Act Density 0.127%

    No Known Activations