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

    Neuronpedia

    INDEX
    Explanations

    .text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     motivo
    -0.08
    Simulation
    -0.07
    que
    -0.07
    Neo
    -0.07
     sens
    -0.07
    model
    -0.07
     из
    -0.07
     Assuming
    -0.07
    墩
    -0.07
     pil
    -0.07
    POSITIVE LOGITS
     winters
    0.08
    UIAlertView
    0.07
     giveaway
    0.07
     Gay
    0.07
    יף
    0.07
    лю
    0.07
     לעבוד
    0.07
     playerName
    0.07
     glEnable
    0.07
    _outline
    0.07
    Act Density 0.009%

    No Known Activations