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

    Neuronpedia

    INDEX
    Explanations

    timestamps and times

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ouss
    0.41
     carbs
    0.40
     polysaccharides
    0.40
    ್ರೆ
    0.39
     सुविधाएं
    0.38
    对象
    0.38
     πολι
    0.38
     মানুষের
    0.38
    glyphs
    0.38
    ሳይ
    0.38
    POSITIVE LOGITS
     elapsed
    0.53
     після
    0.52
     minutos
    0.50
     weiteren
    0.50
     minuto
    0.49
     weitere
    0.48
     వెంటనే
    0.48
     вслед
    0.47
     imedi
    0.47
     время
    0.46
    Act Density 0.057%

    No Known Activations