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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     дописавши
    -0.64
     autorytatywna
    -0.54
    tvguidetime
    -0.52
    "):
    -0.46
    UNCIL
    -0.45
    .
    -0.45
    bewerken
    -0.45
     Heere
    -0.45
    ]').
    -0.44
    osomal
    -0.44
    POSITIVE LOGITS
     promozione
    0.60
    http
    0.55
    ljiv
    0.54
     gräns
    0.54
     garanzia
    0.54
     rowspan
    0.54
     möjligt
    0.53
     genoemd
    0.52
    Before
    0.52
    DOCTYPE
    0.52
    Act Density 0.010%

    No Known Activations