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

    Neuronpedia

    INDEX
    Explanations

    office closures, holidays

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /package
    -0.08
     getName
    -0.07
    (header
    -0.07
     collectively
    -0.07
    обы
    -0.07
     miscellaneous
    -0.07
     formations
    -0.07
     Obtain
    -0.07
    Hat
    -0.07
     Kansas
    -0.07
    POSITIVE LOGITS
    折磨
    0.08
    DonaldTrump
    0.07
    ("%.
    0.07
     ż
    0.07
     horr
    0.07
     insulting
    0.07
    触及
    0.06
     irm
    0.06
     chmod
    0.06
    ẅ
    0.06
    Act Density 0.036%

    No Known Activations