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

    Neuronpedia

    INDEX
    Explanations

    language about consumers and satisfying their desires

    oai_token-act-pair · gemini-2.0-flash

    desire

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AccessorTable
    -0.64
    usercontent
    -0.64
    Bioaccumulative
    -0.63
    ExecuteReader
    -0.63
    SaveChangesAsync
    -0.59
    ViewFeatures
    -0.58
    تقاوى
    -0.54
    protoc
    -0.54
    ilmente
    -0.54
    labelledby
    -0.54
    POSITIVE LOGITS
     desire
    0.69
     want
    0.68
     wish
    0.67
     interest
    0.66
     propOrder
    0.63
     defire
    0.62
    want
    0.60
     wanting
    0.59
    InstanceState
    0.57
     necessity
    0.55
    Act Density 2.992%

    No Known Activations