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

    Neuronpedia

    INDEX
    Explanations

    January Initiative held

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ermög
    0.49
     Pancakes
    0.40
    xymatrix
    0.38
     umož
    0.37
    वानिव
    0.37
    マンス
    0.36
    无奈
    0.36
    قط
    0.36
     پلا
    0.36
    chooser
    0.35
    POSITIVE LOGITS
     cle
    0.42
    清
    0.42
     shadow
    0.40
    cle
    0.40
     signal
    0.40
     indications
    0.40
     disturbances
    0.39
     step
    0.38
     django
    0.38
     atmospheric
    0.37
    Act Density 0.002%

    No Known Activations