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

    Neuronpedia

    INDEX
    Explanations

    academic papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    edom
    -0.07
    ポイ
    -0.07
    CSR
    -0.07
    猢
    -0.07
    .plot
    -0.07
     TEXT
    -0.07
     Mango
    -0.07
     noise
    -0.07
    .pageX
    -0.06
    שלום
    -0.06
    POSITIVE LOGITS
    _fwd
    0.07
     dạy
    0.07
    _Item
    0.07
    አ
    0.07
    准
    0.07
    .RowCount
    0.07
    ometown
    0.07
    oward
    0.07
    干预
    0.07
     nue
    0.07
    Act Density 0.049%

    No Known Activations