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

    Neuronpedia

    INDEX
    Explanations

    code with conditional logic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .steps
    -0.07
     مجموع
    -0.07
    -B
    -0.07
     pipes
    -0.06
     في
    -0.06
    (xpath
    -0.06
     sólo
    -0.06
    �
    -0.06
    ейств
    -0.06
    Flat
    -0.06
    POSITIVE LOGITS
    [parent
    0.06
     Moroccan
    0.06
     г
    0.06
     моз
    0.06
     bạn
    0.06
     elderly
    0.06
     mojo
    0.06
    .removeFrom
    0.06
    朱
    0.06
     supervisor
    0.06
    Act Density 0.047%

    No Known Activations