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

    Neuronpedia

    INDEX
    Explanations

    Problems and complaints

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    озі
    -0.07
    trusted
    -0.07
    located
    -0.07
     Principle
    -0.06
    ну
    -0.06
     如果
    -0.06
     діє
    -0.06
    enerima
    -0.06
    _>
    -0.06
    έρ
    -0.06
    POSITIVE LOGITS
     else
    0.07
     Taken
    0.06
     downhill
    0.06
    �
    0.06
     Hemisphere
    0.06
     SAX
    0.06
     gul
    0.06
     홍
    0.06
    sav
    0.06
     GraphQL
    0.06
    Act Density 0.056%

    No Known Activations