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

    Neuronpedia

    INDEX
    Explanations

    r

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    TypeName
    -0.06
     scandals
    -0.06
    _Pin
    -0.06
    oplay
    -0.06
     FDA
    -0.06
    vinces
    -0.06
    losures
    -0.06
    fin
    -0.06
    φορά
    -0.06
    ==========
    -0.06
    POSITIVE LOGITS
     Hispanic
    0.07
    ernaut
    0.07
     mili
    0.06
     validates
    0.06
     เค
    0.06
     republik
    0.06
     yıldır
    0.06
     München
    0.06
     euth
    0.06
     OTHER
    0.06
    Act Density 0.002%

    No Known Activations