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

    Neuronpedia

    INDEX
    Explanations

    AI writing prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     programmable
    -0.07
    ちゃん
    -0.07
    ffects
    -0.07
     antibodies
    -0.07
    刊
    -0.07
    。当然
    -0.07
    ଣ
    -0.07
    typeparam
    -0.07
    358
    -0.06
     concerne
    -0.06
    POSITIVE LOGITS
     Hend
    0.08
     goose
    0.08
     harmful
    0.08
     صادر
    0.08
     alku
    0.08
     undue
    0.08
    -length
    0.08
     Saving
    0.08
     anderes
    0.08
     iniciado
    0.08
    Act Density 0.024%

    No Known Activations