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

    Neuronpedia

    INDEX
    Explanations

    Academic writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Erin
    -0.07
    cken
    -0.06
    ndern
    -0.06
    imiento
    -0.06
    いる
    -0.06
    _sz
    -0.06
     Sanford
    -0.06
    _bundle
    -0.06
     Soros
    -0.06
    13
    -0.06
    POSITIVE LOGITS
     tokenize
    0.07
     pym
    0.07
    _shape
    0.07
    itemName
    0.07
     مواط
    0.06
    cdot
    0.06
    >{
    0.06
    .quant
    0.06
    urvey
    0.06
     profession
    0.06
    Act Density 0.034%

    No Known Activations