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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bookmark
    -0.07
    #\
    -0.07
     ASP
    -0.07
    _cv
    -0.06
     Vladim
    -0.06
    .ic
    -0.06
     indicator
    -0.06
     Massage
    -0.06
     supermarket
    -0.06
     flagged
    -0.06
    POSITIVE LOGITS
    ofstream
    0.06
     Gh
    0.06
    _RAM
    0.06
    .Guna
    0.06
    (environment
    0.06
    емые
    0.06
     διά
    0.06
    aliyet
    0.06
     Rou
    0.06
    사는
    0.06
    Act Density 0.199%

    No Known Activations