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

    Neuronpedia

    INDEX
    Explanations

    Image filtering

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    увався
    -0.08
    bubble
    -0.06
     Dialogue
    -0.06
    entication
    -0.06
    들도
    -0.06
     Jihad
    -0.06
     Religious
    -0.06
    uter
    -0.06
    routes
    -0.06
    رود
    -0.06
    POSITIVE LOGITS
    (File
    0.07
     آمار
    0.07
    oxy
    0.07
     primaryStage
    0.06
    форма
    0.06
     líder
    0.06
    abo
    0.06
     Worlds
    0.06
    _smooth
    0.06
    .flatten
    0.06
    Act Density 0.013%

    No Known Activations