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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    StoryboardSegue
    -0.65
    elemField
    -0.60
    jgl
    -0.54
    oa̍t
    -0.52
    protoimpl
    -0.51
    -0.51
    ContentLoaded
    -0.49
    noscript
    -0.49
     abandonado
    -0.47
     betweenstory
    -0.47
    POSITIVE LOGITS
     EconPapers
    0.69
     reason
    0.67
     man
    0.59
     object
    0.59
     basis
    0.58
     inspiration
    0.58
    ContentAsync
    0.57
     direct
    0.56
     only
    0.56
    </thead>
    0.56
    Act Density 0.005%

    No Known Activations