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

    Neuronpedia

    INDEX
    Explanations

    longer pieces or stories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Casper
    0.49
     degrés
    0.48
     Burlington
    0.42
    攝影
    0.42
    告示
    0.41
    affer
    0.41
    setKeepCallback
    0.41
    لو
    0.40
    फ़
    0.40
    蘆
    0.40
    POSITIVE LOGITS
     труб
    0.50
     дли
    0.46
    KES
    0.44
    profitable
    0.43
    ol
    0.42
     ristrutt
    0.42
     caric
    0.42
     острова
    0.42
     zuletzt
    0.42
    Ley
    0.42
    Act Density 0.001%

    No Known Activations