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

    Neuronpedia

    INDEX
    Explanations

    There

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    r
    0.50
    adolu
    0.45
    ﺙ
    0.45
    arange
    0.45
     العملية
    0.45
    arity
    0.44
    мето
    0.44
    adati
    0.44
    mitted
    0.43
    lene
    0.42
    POSITIVE LOGITS
    י
    0.52
    Lack
    0.52
    й
    0.50
    实在
    0.49
    ї
    0.48
     lack
    0.48
     জায়গা
    0.48
     pratiquer
    0.47
    ي
    0.46
    ৫
    0.46
    Act Density 0.000%

    No Known Activations