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

    Neuronpedia

    INDEX
    Explanations

    South

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ajas
    -0.07
     familia
    -0.07
    (&$
    -0.07
     Tucker
    -0.06
    幼
    -0.06
     Carlo
    -0.06
    unun
    -0.06
     Johan
    -0.06
    ược
    -0.06
     Mapping
    -0.06
    POSITIVE LOGITS
    Caps
    0.07
     frivol
    0.07
    nome
    0.06
     Speakers
    0.06
    vvm
    0.06
     Fucked
    0.06
    finder
    0.06
    ρκεια
    0.06
     CGFloat
    0.06
    .sb
    0.06
    Act Density 0.004%

    No Known Activations