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

    Neuronpedia

    INDEX
    Explanations

    p

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ults
    -0.07
    بالإنجليزية
    -0.07
     BOOK
    -0.07
     Maar
    -0.06
     book
    -0.06
     Creek
    -0.06
    -book
    -0.06
     Fu
    -0.06
    \Resources
    -0.06
    Disposition
    -0.06
    POSITIVE LOGITS
     incompet
    0.07
    quiring
    0.07
     sympath
    0.07
    graphql
    0.07
    PM
    0.06
     Wise
    0.06
    whole
    0.06
    ottle
    0.06
     setUp
    0.06
    depend
    0.06
    Act Density 0.001%

    No Known Activations