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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monk
    -0.07
     apprentice
    -0.07
     John
    -0.07
    bugs
    -0.07
    iao
    -0.07
     připoj
    -0.07
    appName
    -0.06
    Literal
    -0.06
    /problem
    -0.06
     empez
    -0.06
    POSITIVE LOGITS
    STORE
    0.07
    _CITY
    0.07
     OPP
    0.06
    iggins
    0.06
    是一个
    0.06
     ú
    0.06
     "-"↵
    0.06
    ันธ
    0.06
    IVEN
    0.06
    하며
    0.06
    Act Density 0.035%

    No Known Activations