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

    Neuronpedia

    INDEX
    Explanations

    string type in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     จะ
    0.48
    ན
    0.48
     স্থাপন
    0.47
     progressivement
    0.47
     modalCard
    0.46
    marshalN
    0.45
     выбрать
    0.45
     reasonableness
    0.44
    lia
    0.44
     ሀ
    0.44
    POSITIVE LOGITS
     sentimos
    0.44
     patas
    0.42
    حيان
    0.41
    Monitor
    0.41
    走
    0.39
     monitor
    0.39
    меча
    0.39
    нинг
    0.38
    తులు
    0.38
    ської
    0.38
    Act Density 0.000%

    No Known Activations