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

    Neuronpedia

    INDEX
    Explanations

    areas of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     anns
    0.39
    နာ
    0.39
     얼굴
    0.39
     affili
    0.38
    kates
    0.38
    िवा
    0.38
    пример
    0.38
    コーチ
    0.37
    atience
    0.37
    kirche
    0.36
    POSITIVE LOGITS
     छ
    0.43
    起
    0.42
     Six
    0.41
    aplan
    0.40
     Click
    0.39
     Química
    0.39
    竭
    0.39
     six
    0.38
     आइस
    0.38
     मु
    0.38
    Act Density 0.000%

    No Known Activations