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

    Neuronpedia

    INDEX
    Explanations

    Unstructured, varied text sources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    blood
    -0.07
     Blond
    -0.07
    Vehicle
    -0.06
    -0.06
    alon
    -0.06
     inertia
    -0.06
    _positive
    -0.06
    -elect
    -0.06
     irrit
    -0.06
     Republicans
    -0.06
    POSITIVE LOGITS
     chị
    0.06
     millones
    0.06
     examples
    0.06
     removes
    0.06
    tsx
    0.06
    گیری
    0.06
     ISS
    0.06
    CreateTime
    0.06
     yılında
    0.06
    rons
    0.06
    Act Density 0.000%

    No Known Activations