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

    Neuronpedia

    INDEX
    Explanations

    structured lists and instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ip
    0.43
    kennt
    0.42
    blers
    0.41
    ž
    0.40
    icher
    0.40
     DMBT
    0.40
    umni
    0.39
    REGEX
    0.39
     Leistungs
    0.39
    ية
    0.39
    POSITIVE LOGITS
    landmark
    0.48
     parejas
    0.45
     инструкции
    0.45
    랙
    0.43
     глав
    0.43
     residuals
    0.42
     landmark
    0.42
     момент
    0.42
    ≌
    0.42
    ිට
    0.42
    Act Density 0.002%

    No Known Activations