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

    Neuronpedia

    INDEX
    Explanations

    License

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंर
    -0.07
    ază
    -0.06
     переда
    -0.06
    ери
    -0.06
     erót
    -0.06
    irection
    -0.06
    ्बर
    -0.06
     plunder
    -0.06
     hätte
    -0.06
     Coat
    -0.06
    POSITIVE LOGITS
     InputDecoration
    0.08
    807
    0.07
    (options
    0.06
     Li
    0.06
     Gaw
    0.06
     Dor
    0.06
    .Is
    0.06
    Li
    0.06
    183
    0.06
    (doc
    0.06
    Act Density 0.003%

    No Known Activations