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

    Neuronpedia

    INDEX
    Explanations

    convention

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     AccessToken
    -0.07
    Nİ
    -0.07
     THREAD
    -0.07
     sıcak
    -0.07
    .atomic
    -0.06
     мину
    -0.06
     myths
    -0.06
    高校
    -0.06
    лег
    -0.06
     refurb
    -0.06
    POSITIVE LOGITS
     botanical
    0.07
    queen
    0.07
    fel
    0.06
     roy
    0.06
    bad
    0.06
    931
    0.06
    _cid
    0.06
    شار
    0.06
    ("!
    0.06
    DONE
    0.06
    Act Density 0.009%

    No Known Activations