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

    Neuronpedia

    INDEX
    Explanations

    into

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     uomo
    -0.07
    фек
    -0.07
    Hope
    -0.07
     escape
    -0.06
     feeder
    -0.06
    utin
    -0.06
    ミュ
    -0.06
     mf
    -0.06
    ادل
    -0.06
    国
    -0.06
    POSITIVE LOGITS
    BeenCalled
    0.07
    ––
    0.07
     bios
    0.07
     Investigation
    0.06
     reperc
    0.06
     breadcrumb
    0.06
     MDMA
    0.06
    под
    0.06
     investigates
    0.06
     depuis
    0.06
    Act Density 0.028%

    No Known Activations