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

    Neuronpedia

    INDEX
    Explanations

    inhibitors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     robes
    -0.07
     Neville
    -0.07
    ně
    -0.06
     films
    -0.06
     ledna
    -0.06
    ایان
    -0.06
     січня
    -0.06
    kou
    -0.06
     homme
    -0.06
    면적
    -0.06
    POSITIVE LOGITS
    Certain
    0.07
     UINT
    0.07
     conectar
    0.06
     Certain
    0.06
     tremendous
    0.06
    going
    0.06
     Kürt
    0.06
    <context
    0.06
    .statusCode
    0.06
     SUS
    0.06
    Act Density 0.024%

    No Known Activations