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

    Neuronpedia

    INDEX
    Explanations

    be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _FORE
    -0.06
    .exclude
    -0.06
     Louis
    -0.06
    ध
    -0.06
     oats
    -0.06
    026
    -0.06
    uf
    -0.06
    ン�
    -0.06
    CADE
    -0.06
     expressions
    -0.06
    POSITIVE LOGITS
     příč
    0.07
     erotisk
    0.06
    しており
    0.06
    ”—
    0.06
    _operand
    0.06
     WINDOW
    0.06
     pardon
    0.06
     IReadOnly
    0.06
     clocks
    0.06
     incumb
    0.06
    Act Density 0.063%

    No Known Activations