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

    Neuronpedia

    INDEX
    Explanations

    Violation Theory

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     novos
    0.50
     желез
    0.46
    زين
    0.46
     nous
    0.44
     rainwater
    0.44
     الماء
    0.44
     आओ
    0.43
    叓
    0.43
     biomass
    0.42
     aquarium
    0.42
    POSITIVE LOGITS
    tooltip
    0.45
    AGING
    0.44
    Button
    0.43
    stand
    0.42
    walten
    0.42
    Ja
    0.42
    Step
    0.42
    temporal
    0.41
    '
    0.40
    Tuple
    0.40
    Act Density 0.000%

    No Known Activations