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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     data
    -0.07
    /";↵↵
    -0.07
    table
    -0.07
     dwar
    -0.06
    _activate
    -0.06
     dors
    -0.06
     وص
    -0.06
    /command
    -0.06
    .ap
    -0.06
    /Set
    -0.06
    POSITIVE LOGITS
     SOS
    0.07
     하는
    0.07
    .Cl
    0.07
     só
    0.07
    .NaN
    0.06
     Clinic
    0.06
    到的
    0.06
     IIC
    0.06
     pak
    0.06
     omez
    0.06
    Act Density 0.334%

    No Known Activations