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

    Neuronpedia

    INDEX
    Explanations

    th

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cocina
    -0.07
     palabra
    -0.07
     Bangalore
    -0.06
    、な
    -0.06
     frying
    -0.06
    kę
    -0.06
    conversation
    -0.06
     Sheets
    -0.06
    ında
    -0.06
     Bris
    -0.06
    POSITIVE LOGITS
     Literature
    0.07
     instrumental
    0.07
     television
    0.07
     روشن
    0.07
    ResponseStatus
    0.06
    eight
    0.06
    فة
    0.06
     Chevrolet
    0.06
     ej
    0.06
    _COMPONENT
    0.06
    Act Density 0.004%

    No Known Activations