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

    Neuronpedia

    INDEX
    Explanations

    code symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enos
    -0.06
    _options
    -0.06
     Grad
    -0.06
    -native
    -0.06
     disabilities
    -0.06
    _DOWN
    -0.06
    Nom
    -0.06
    radio
    -0.06
    んでいる
    -0.06
    SEO
    -0.05
    POSITIVE LOGITS
    -Encoding
    0.07
    _CHARS
    0.07
    ?>">↵
    0.07
    thood
    0.07
     Wichita
    0.07
     Güney
    0.06
    .Root
    0.06
    럽
    0.06
     Sioux
    0.06
    []=
    0.06
    Act Density 0.105%

    No Known Activations