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

    Neuronpedia

    INDEX
    Explanations

    scientific and medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Race
    -0.06
     gener
    -0.06
    ergy
    -0.06
     cure
    -0.06
     dere
    -0.06
    BU
    -0.06
    贝
    -0.06
     agli
    -0.06
    man
    -0.06
     Genesis
    -0.06
    POSITIVE LOGITS
     OH
    0.07
    -topic
    0.07
    unately
    0.07
    oh
    0.07
    _this
    0.07
    _robot
    0.07
    ,proto
    0.07
    Tonight
    0.07
     Himal
    0.06
     Subscribe
    0.06
    Act Density 0.011%

    No Known Activations