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

    Neuronpedia

    INDEX
    Explanations

    Code environment

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    сл
    -0.07
     retrospect
    -0.06
     Running
    -0.06
    Feb
    -0.06
     pena
    -0.06
     saya
    -0.06
     Tried
    -0.06
    Datum
    -0.06
     USERNAME
    -0.06
     relinqu
    -0.06
    POSITIVE LOGITS
     groceries
    0.07
     Alice
    0.07
    bane
    0.07
     대해
    0.06
    -trash
    0.06
     rooted
    0.06
    :].
    0.06
     Jou
    0.06
     POD
    0.06
     minimalist
    0.06
    Act Density 0.162%

    No Known Activations