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

    Neuronpedia

    INDEX
    Explanations

    negative bodily sensations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    imus
    -0.08
     paris
    -0.07
    chrom
    -0.07
     mange
    -0.06
     Berk
    -0.06
    olas
    -0.06
     speeches
    -0.06
     dici
    -0.06
     administered
    -0.06
     мала
    -0.06
    POSITIVE LOGITS
    ownload
    0.07
     Mazda
    0.06
     unity
    0.06
    comma
    0.06
    //
↵
↵
    0.06
    ']->
    0.06
    rosse
    0.06
     Tunnel
    0.06
     직접
    0.06
    Making
    0.06
    Act Density 0.028%

    No Known Activations