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

    Neuronpedia

    INDEX
    Explanations

    Open

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afort
    -0.07
    思考
    -0.06
    utsch
    -0.06
    describe
    -0.06
     Laure
    -0.06
    redits
    -0.06
    _Show
    -0.06
     силу
    -0.06
    _member
    -0.06
     alarmed
    -0.06
    POSITIVE LOGITS
    (sd
    0.07
     Operational
    0.06
     {!!
    0.06
    启
    0.06
    /*!
    0.06
    aguay
    0.06
     seasoned
    0.06
    	tr
    0.06
    ("`
    0.06
     opin
    0.06
    Act Density 0.001%

    No Known Activations