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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deste
    -0.07
    .mime
    -0.07
    ulação
    -0.07
    _HERE
    -0.06
    nameof
    -0.06
     해야
    -0.06
    prompt
    -0.06
     Boulder
    -0.06
     Liu
    -0.06
    (super
    -0.06
    POSITIVE LOGITS
    	Route
    0.07
    ！↵
    0.06
    ortic
    0.06
     OE
    0.06
    。↵
    0.06
     инструмент
    0.06
     ek
    0.06
     Providing
    0.06
     or
    0.06
     потом
    0.06
    Act Density 0.020%

    No Known Activations