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

    Neuronpedia

    INDEX
    Explanations

    friend

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िलन
    -0.07
    _NODES
    -0.07
     testData
    -0.06
    interactive
    -0.06
    accounts
    -0.06
    uggestions
    -0.06
    BUM
    -0.06
    _sock
    -0.06
    .setup
    -0.06
    Trust
    -0.06
    POSITIVE LOGITS
     sen
    0.07
     Armed
    0.07
     περ
    0.06
    oner
    0.06
     bunu
    0.06
     Lv
    0.06
    <td
    0.06
    ิวเตอร
    0.06
     Compass
    0.06
     petites
    0.06
    Act Density 0.038%

    No Known Activations