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

    Neuronpedia

    INDEX
    Explanations

    historical period/technology level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owan
    -0.07
    _ctl
    -0.06
     Yelp
    -0.06
     kelim
    -0.06
    アルバ
    -0.06
    ncias
    -0.06
     영어
    -0.06
     Filme
    -0.06
     البي
    -0.06
    /cupertino
    -0.06
    POSITIVE LOGITS
     Islamic
    0.08
    _absolute
    0.07
    arsi
    0.07
    lic
    0.06
     locksmith
    0.06
    ieder
    0.06
     affordability
    0.06
     благ
    0.06
    تق
    0.06
    argout
    0.06
    Act Density 0.008%

    No Known Activations