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

    Neuronpedia

    INDEX
    Explanations

    Software development documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kathryn
    -0.07
     stereotypes
    -0.06
     Hydro
    -0.06
     земли
    -0.06
    浜
    -0.06
     deben
    -0.06
     satisf
    -0.06
    Qualifier
    -0.06
     Similarly
    -0.06
    ccc
    -0.06
    POSITIVE LOGITS
    ाजन
    0.07
     نظام
    0.07
    (song
    0.06
    ~":"
    0.06
    .setProgress
    0.06
    (format
    0.06
    ython
    0.06
     cout
    0.06
     mattered
    0.06
    SPARENT
    0.06
    Act Density 0.098%

    No Known Activations