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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    >Type
    -0.08
    _REPORT
    -0.08
     summarizes
    -0.07
     Christine
    -0.07
    <pcl
    -0.07
     Earl
    -0.07
    _For
    -0.07
    _steps
    -0.07
    .inventory
    -0.07
    .func
    -0.07
    POSITIVE LOGITS
    思い
    0.06
    deaux
    0.06
    294
    0.06
    jet
    0.06
     ok
    0.06
     كامل
    0.05
     чтобы
    0.05
    Namespace
    0.05
    亞
    0.05
    سك
    0.05
    Act Density 0.037%

    No Known Activations