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

    Neuronpedia

    INDEX
    Explanations

    yum

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    981
    -0.07
    ายน
    -0.07
     parameters
    -0.06
     frosting
    -0.06
    _err
    -0.06
    _filt
    -0.06
    Repositories
    -0.06
    ictures
    -0.06
     rdf
    -0.06
    _stdout
    -0.06
    POSITIVE LOGITS
     Toxic
    0.07
     seniors
    0.07
    xic
    0.06
    rys
    0.06
     inertia
    0.06
    　ヽ
    0.06
    _rent
    0.06
    ző
    0.06
    ustral
    0.06
    ком
    0.06
    Act Density 0.003%

    No Known Activations