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

    Neuronpedia

    INDEX
    Explanations

    advantages and disadvantages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Opp
    -0.07
     depend
    -0.07
     Bew
    -0.07
     Etsy
    -0.07
     synonymous
    -0.06
    搭载
    -0.06
     géné
    -0.06
    IND
    -0.06
    钍
    -0.06
     ende
    -0.06
    POSITIVE LOGITS
     credential
    0.07
    جري
    0.07
    layan
    0.07
    appropriate
    0.07
    observable
    0.07
    ificial
    0.07
     трех
    0.07
     formal
    0.06
    améliorer
    0.06
     multiple
    0.06
    Act Density 0.035%

    No Known Activations