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

    Neuronpedia

    INDEX
    Explanations

    website/magazine content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     기억
    -0.07
    女性
    -0.07
    throat
    -0.06
     Năm
    -0.06
    .def
    -0.06
    орг
    -0.06
    �
    -0.06
    pixels
    -0.06
     некотор
    -0.06
     Về
    -0.06
    POSITIVE LOGITS
     Kaepernick
    0.07
    悠
    0.07
     铁
    0.07
    formance
    0.07
     dominance
    0.06
     dém
    0.06
    '];
↵
    0.06
     \↵↵
    0.06
    イド
    0.06
     lng
    0.06
    Act Density 0.050%

    No Known Activations