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

    Neuronpedia

    INDEX
    Explanations

    data manipulation and analysis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Classes
    -0.06
    285
    -0.06
    ($('.
    -0.06
     Wen
    -0.06
    Ars
    -0.06
    284
    -0.06
    ennen
    -0.06
    Roman
    -0.06
     tangent
    -0.06
    gypt
    -0.06
    POSITIVE LOGITS
     registered
    0.07
     LICENSE
    0.07
    :N
    0.07
    yahoo
    0.06
     gint
    0.06
     SEAL
    0.06
     standalone
    0.06
     selective
    0.06
     style
    0.06
    .Native
    0.06
    Act Density 0.995%

    No Known Activations