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

    Neuronpedia

    INDEX
    Explanations

    measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _magic
    -0.07
    _Ptr
    -0.06
    .COMP
    -0.06
    ΗΜ
    -0.06
     paralle
    -0.06
    Susp
    -0.06
     zástup
    -0.06
     vhodné
    -0.06
    やす
    -0.06
    كومة
    -0.06
    POSITIVE LOGITS
    encers
    0.07
     Contracts
    0.06
    فع
    0.06
     unleashed
    0.06
    .Style
    0.06
    assi
    0.06
     Clyde
    0.06
    _lista
    0.06
     desire
    0.06
    ={`/
    0.06
    Act Density 0.210%

    No Known Activations