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

    Neuronpedia

    INDEX
    Explanations

    origins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dialog
    -0.07
    _DOT
    -0.06
     usando
    -0.06
     прит
    -0.06
     Broadway
    -0.06
     Gus
    -0.06
    getConfig
    -0.06
    év
    -0.05
     разд
    -0.05
    ))*(
    -0.05
    POSITIVE LOGITS
    ผล
    0.07
     Forge
    0.07
     Producer
    0.07
    registr
    0.07
     fire
    0.07
     stu
    0.07
     YY
    0.07
    obe
    0.07
     nonsense
    0.06
     sorting
    0.06
    Act Density 0.033%

    No Known Activations