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

    Neuronpedia

    INDEX
    Explanations

    explaining processes or tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Music
    0.50
     Periods
    0.49
    élix
    0.49
    Leaders
    0.47
     परमात्मा
    0.46
    Percent
    0.46
    Sugar
    0.45
    Actors
    0.45
     हुन्छ
    0.45
    伈
    0.45
    POSITIVE LOGITS
     jeep
    0.45
     ferocious
    0.44
     casco
    0.44
     strap
    0.43
     salida
    0.43
    اويه
    0.43
     Aliexpress
    0.43
     cashmere
    0.43
     cabin
    0.43
     kab
    0.42
    Act Density 0.000%

    No Known Activations