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

    Neuronpedia

    INDEX
    Explanations

    Generally positive descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unpopular
    -0.07
    Incorrect
    -0.07
    elmet
    -0.06
     Judgment
    -0.06
     MAV
    -0.06
     spéc
    -0.06
    فتم
    -0.06
     mh
    -0.06
     establishes
    -0.06
    ęd
    -0.06
    POSITIVE LOGITS
    724
    0.08
     devour
    0.07
    joining
    0.07
    /x
    0.06
    TagName
    0.06
    suming
    0.06
    _terms
    0.06
     dashboard
    0.06
    panies
    0.06
    (Media
    0.06
    Act Density 0.176%

    No Known Activations