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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     monopol
    -0.07
    ض
    -0.06
     resto
    -0.06
     było
    -0.06
     Phantom
    -0.06
    .logo
    -0.06
    017
    -0.06
     Grad
    -0.06
    vat
    -0.06
    ेम
    -0.06
    POSITIVE LOGITS
     recycled
    0.06
    .Then
    0.06
    kins
    0.06
    plete
    0.06
     TCP
    0.06
     lest
    0.06
     siyas
    0.06
     airport
    0.06
    locations
    0.06
    كس
    0.06
    Act Density 0.003%

    No Known Activations