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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     _{
    -0.07
     John
    -0.07
     Vall
    -0.06
     coefficients
    -0.06
     titular
    -0.06
    bars
    -0.06
    Лю
    -0.06
     Developing
    -0.06
     Constantin
    -0.06
     de
    -0.06
    POSITIVE LOGITS
    gc
    0.07
    ับร
    0.07
     مهم
    0.06
    ={!
    0.06
    buquerque
    0.06
    leanup
    0.06
    	bg
    0.06
    _any
    0.06
    figures
    0.06
     буде
    0.06
    Act Density 0.000%

    No Known Activations