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

    Neuronpedia

    INDEX
    Explanations

    informational texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rempl
    -0.08
     >>>
    -0.06
     dati
    -0.06
    说
    -0.06
    -0.06
    완
    -0.06
     alive
    -0.06
     Milf
    -0.06
    ors
    -0.05
     eriş
    -0.05
    POSITIVE LOGITS
    >'
↵
    0.07
    Metro
    0.07
    하다
    0.07
    packet
    0.07
     carbohydrate
    0.06
     Euros
    0.06
     Onion
    0.06
    <Service
    0.06
    .Hand
    0.06
     Civ
    0.06
    Act Density 0.000%

    No Known Activations