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

    Neuronpedia

    INDEX
    Explanations

    Category specific item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     escapar
    0.45
    linearity
    0.43
    Parameterized
    0.42
    Invalid
    0.41
    Incorrect
    0.41
    Leaks
    0.41
    Treat
    0.40
    Plane
    0.39
     Incorrect
    0.38
     kvůli
    0.38
    POSITIVE LOGITS
    টাও
    0.40
     आजही
    0.40
     sophisticated
    0.40
     मोटे
    0.40
    மான
    0.39
     pragmatic
    0.39
     portfolio
    0.39
     procur
    0.39
    を選
    0.38
     practica
    0.38
    Act Density 0.002%

    No Known Activations