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

    Neuronpedia

    INDEX
    Explanations

    Code/Data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     perfume
    -0.07
     stumbling
    -0.06
    	buff
    -0.06
    Pok
    -0.06
     виснов
    -0.06
    .argmax
    -0.06
     thankful
    -0.06
     avent
    -0.06
     près
    -0.06
    ymes
    -0.06
    POSITIVE LOGITS
    _abs
    0.07
    endencies
    0.07
     bạn
    0.06
    mdi
    0.06
     Kaplan
    0.06
     compositions
    0.06
    _DONE
    0.06
    olkata
    0.06
    _COMP
    0.06
     Canton
    0.06
    Act Density 0.091%

    No Known Activations