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

    Neuronpedia

    INDEX
    Explanations

    Scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mitochond
    -0.07
    kip
    -0.06
     Else
    -0.06
     RAF
    -0.06
    kan
    -0.06
    َى
    -0.06
    atient
    -0.06
     Duc
    -0.06
     haf
    -0.06
     Ran
    -0.06
    POSITIVE LOGITS
     웹사이트
    0.07
    urd
    0.07
     showcased
    0.06
     kostenlos
    0.06
    =").
    0.06
    'http
    0.06
    /bind
    0.06
    )(__
    0.06
     сім
    0.06
    办
    0.06
    Act Density 0.008%

    No Known Activations