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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endar
    -0.06
    AVA
    -0.06
     death
    -0.06
    ции
    -0.06
     sucking
    -0.06
     Orden
    -0.06
    يرة
    -0.06
     BOTH
    -0.06
     salir
    -0.06
    ádu
    -0.06
    POSITIVE LOGITS
    _LSB
    0.07
     перевір
    0.07
     ResourceType
    0.06
    ffb
    0.06
    -Identifier
    0.06
     fraudulent
    0.06
     searchString
    0.06
    -roll
    0.06
    .nr
    0.05
    .coordinates
    0.05
    Act Density 0.015%

    No Known Activations