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

    Neuronpedia

    INDEX
    Explanations

    self-description or model identity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tamaños
    0.43
     totalidad
    0.43
     muebles
    0.42
     habilidad
    0.40
    溌
    0.40
     thuế
    0.39
     probabilidad
    0.39
    利率
    0.39
     ejemplos
    0.38
     nacimiento
    0.38
    POSITIVE LOGITS
    s
    0.54
    ер
    0.52
    ERT
    0.52
    Descriptor
    0.52
    ubu
    0.51
    stv
    0.51
     RES
    0.50
    ata
    0.49
    ront
    0.49
     scolded
    0.49
    Act Density 0.001%

    No Known Activations