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

    Neuronpedia

    INDEX
    Explanations

    Technology and science

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ถ
    -0.08
    aların
    -0.07
     The
    -0.07
     foolish
    -0.07
     have
    -0.07
    (files
    -0.06
    Arch
    -0.06
     Суд
    -0.06
     lively
    -0.06
    Networking
    -0.06
    POSITIVE LOGITS
     ',',
    0.06
    ®,
    0.06
    .↵↵↵↵↵↵↵↵↵↵
    0.06
    ísticas
    0.06
    �
    0.06
    genden
    0.06
    onis
    0.06
    alaria
    0.06
     tha
    0.06
     []↵↵↵
    0.06
    Act Density 1.007%

    No Known Activations