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

    Neuronpedia

    INDEX
    Explanations

    rates and frequencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     degree
    0.42
     grado
    0.40
     Degree
    0.39
     비율
    0.38
     รี
    0.37
     compute
    0.36
    GraphicsUnit
    0.36
     を
    0.36
     secretly
    0.36
     seuls
    0.36
    POSITIVE LOGITS
     dönem
    0.47
     Period
    0.45
     аспек
    0.45
     lifecycle
    0.44
    йин
    0.43
     Lifecycle
    0.43
     bản
    0.42
     období
    0.41
    period
    0.41
     обновления
    0.41
    Act Density 0.000%

    No Known Activations