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

    Neuronpedia

    INDEX
    Explanations

    self

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﺗ
    0.43
    ثیر
    0.42
     ګرځنده
    0.42
    گذاری
    0.42
    یاز
    0.41
     remporte
    0.41
     గారి
    0.41
     кілько
    0.41
    یر
    0.40
     শহরে
    0.40
    POSITIVE LOGITS
    ;
    0.46
    kal
    0.44
    kes
    0.44
    forgot
    0.44
    fort
    0.43
    ors
    0.43
    arm
    0.43
     다양
    0.43
    fos
    0.43
    golang
    0.42
    Act Density 0.013%

    No Known Activations