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

    Neuronpedia

    INDEX
    Explanations

    data annotation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IXEL
    -0.06
     celebrity
    -0.06
    _ng
    -0.06
     specimen
    -0.06
     readings
    -0.06
     fout
    -0.06
     fan
    -0.06
     specimens
    -0.06
    142
    -0.06
     Pist
    -0.06
    POSITIVE LOGITS
    李
    0.07
    ตล
    0.06
     borderBottom
    0.06
    atırım
    0.06
     SWAT
    0.06
    免费
    0.06
    ;m
    0.06
    .Item
    0.06
    ổi
    0.06
    谋
    0.06
    Act Density 0.024%

    No Known Activations