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

    Neuronpedia

    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    argo
    -0.07
     bespoke
    -0.07
    ounds
    -0.07
     consul
    -0.07
     Tal
    -0.07
    Soph
    -0.07
    ThanOrEqualTo
    -0.07
    _dead
    -0.06
     поск
    -0.06
    =admin
    -0.06
    POSITIVE LOGITS
                         ↵
    0.07
                               ↵
    0.07
     dj
    0.06
     sæ
    0.06
    (request
    0.06
     двор
    0.06
                             ↵
    0.06
    ุง
    0.06
     літ
    0.06
    '}),↵
    0.06
    Act Density 0.099%

    No Known Activations