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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     [];
    -0.07
     кни
    -0.07
    icing
    -0.07
    _access
    -0.06
     Tracy
    -0.06
    (nullptr
    -0.06
     Starbucks
    -0.06
    ]=>
    -0.06
    mat
    -0.06
    oppable
    -0.06
    POSITIVE LOGITS
     beauty
    0.07
     độ
    0.06
    aylor
    0.06
    amburger
    0.06
    Polygon
    0.06
    ρέ
    0.06
    입
    0.06
    환경
    0.06
     corresponding
    0.06
    decode
    0.06
    Act Density 0.036%

    No Known Activations