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

    Neuronpedia

    INDEX
    Explanations

    Code/Log data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ingestion
    -0.08
    -ob
    -0.08
     completed
    -0.08
    Completed
    -0.08
     appliance
    -0.08
    Lo
    -0.07
    _ob
    -0.07
     assume
    -0.07
     avion
    -0.07
    essie
    -0.07
    POSITIVE LOGITS
     nouv
    0.08
     hậu
    0.08
     Ninth
    0.08
     қа
    0.08
    pth
    0.07
     Jeremiah
    0.07
     والم
    0.07
     ocasiones
    0.07
     nguy
    0.07
     ...(
    0.07
    Act Density 0.018%

    No Known Activations