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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Putin
    -0.08
     spy
    -0.08
     butter
    -0.08
     hairstyles
    -0.08
     senators
    -0.08
     sweater
    -0.07
     vat
    -0.07
     Tencent
    -0.07
     Dilma
    -0.07
     impeachment
    -0.07
    POSITIVE LOGITS
     રાહ
    0.09
    رويد
    0.09
     generators
    0.09
     interplay
    0.08
    ూరు
    0.08
     exhaustive
    0.08
    سطس
    0.08
     awaiting
    0.08
    ונדער
    0.08
     желания
    0.08
    Act Density 0.006%

    No Known Activations