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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .INPUT
    -0.07
    Syntax
    -0.06
     SMART
    -0.06
    	while
    -0.06
    better
    -0.06
     Serv
    -0.06
    _visibility
    -0.06
    .toFloat
    -0.06
    ONLY
    -0.06
     Lex
    -0.06
    POSITIVE LOGITS
     pave
    0.07
    наслідок
    0.06
    _wave
    0.06
     Ply
    0.06
    지막
    0.06
    .eq
    0.06
     Dow
    0.06
    扬
    0.06
    	wp
    0.06
     адрес
    0.06
    Act Density 0.007%

    No Known Activations