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

    Neuronpedia

    INDEX
    Explanations

    instructions and advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cancel
    -0.07
     通
    -0.06
     cash
    -0.06
     Pat
    -0.06
     BUS
    -0.06
    ivering
    -0.06
    ENTIAL
    -0.06
    	timeout
    -0.06
    comed
    -0.06
     pregn
    -0.06
    POSITIVE LOGITS
     rehabilitation
    0.07
     Enlightenment
    0.07
     Wave
    0.07
    _LSB
    0.06
    .prototype
    0.06
     }
↵
    0.06
    __;↵
    0.06
    (TokenType
    0.06
     заболевания
    0.06
    _lv
    0.06
    Act Density 0.003%

    No Known Activations