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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Elm
    -0.08
     sizeable
    -0.08
    enso
    -0.08
    _math
    -0.07
     mug
    -0.07
     Christianity
    -0.07
     үлкен
    -0.07
     examinations
    -0.07
     hefty
    -0.07
     praxis
    -0.07
    POSITIVE LOGITS
    :id
    0.08
    :length
    0.08
    .relationship
    0.07
    geht
    0.07
     caste
    0.07
    0.07
    :_
    0.07
     respecto
    0.07
     waktu
    0.07
     Macau
    0.07
    Act Density 0.011%
    No Known Activations