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

    Neuronpedia

    INDEX
    Explanations

    Programming syntax

    np_max-act · gemini-2.0-flash

    code implementations for games in Python.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     timestep
    -0.07
    ARG
    -0.07
    occer
    -0.06
    าคาร
    -0.06
    RefCount
    -0.06
    intree
    -0.06
    _Index
    -0.06
    yclerView
    -0.06
    (Message
    -0.06
    WithValue
    -0.06
    POSITIVE LOGITS
     фот
    0.06
     кас
    0.06
     KM
    0.06
     المد
    0.06
     کار
    0.06
     gerçekleştir
    0.06
     sân
    0.06
     someone
    0.06
    ías
    0.06
     max
    0.06
    Act Density 0.007%

    No Known Activations