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

    Neuronpedia

    INDEX
    Explanations

    Windows features and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    placements
    -0.10
     фан
    -0.09
     Finals
    -0.08
     Toxic
    -0.08
     soucis
    -0.08
     అభిమాన
    -0.08
    สูง
    -0.08
     Ducati
    -0.08
    .Invariant
    -0.08
     mukana
    -0.08
    POSITIVE LOGITS
    _enable
    0.08
    Prere
    0.08
     सक्षम
    0.08
     liik
    0.08
     ಕ್ರಮ
    0.08
     தட
    0.07
     conductive
    0.07
     "\
    0.07
    @Enable
    0.07
     ["
    0.07
    Act Density 0.006%

    No Known Activations