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

    Neuronpedia

    INDEX
    Explanations

    generally English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pox
    0.46
    т
    0.46
    ну
    0.45
    ковь
    0.45
     obstetric
    0.44
     масте
    0.43
    ैंड
    0.42
    торов
    0.42
    ವ್
    0.41
     quail
    0.41
    POSITIVE LOGITS
    Fly
    0.49
     tratados
    0.46
     Declaration
    0.46
     Fly
    0.45
     Primer
    0.45
     maravilh
    0.44
    را
    0.44
    DB
    0.44
    AF
    0.43
     bakan
    0.43
    Act Density 0.001%

    No Known Activations