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

    Neuronpedia

    INDEX
    Explanations

    query

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drums
    -0.07
     بول
    -0.07
     Sticky
    -0.06
     counterfeit
    -0.06
    destroy
    -0.06
    -wing
    -0.06
     gore
    -0.06
     Gall
    -0.06
    SAFE
    -0.06
     taxing
    -0.06
    POSITIVE LOGITS
    CON
    0.07
     strs
    0.06
     ресурс
    0.06
    ท
    0.06
     Assange
    0.06
    建议
    0.06
    λού
    0.06
    netinet
    0.06
     Poss
    0.06
     Kıs
    0.06
    Act Density 0.000%

    No Known Activations