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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _AB
    -0.08
    .Draw
    -0.07
     CircularProgress
    -0.07
    Overlap
    -0.07
     heroin
    -0.07
    대로
    -0.07
     orbital
    -0.07
     limp
    -0.07
     вывод
    -0.06
     reporting
    -0.06
    POSITIVE LOGITS
     muttered
    0.06
     MacDonald
    0.06
    ály
    0.06
    formerly
    0.06
    φαρ
    0.06
    agnost
    0.06
     трохи
    0.06
    čku
    0.06
     คาส
    0.06
    -describedby
    0.06
    Act Density 0.000%

    No Known Activations