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

    Neuronpedia

    INDEX
    Explanations

    non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rent
    -0.08
     rent
    -0.08
     üzerinde
    -0.07
     parques
    -0.07
     выв
    -0.07
    atig
    -0.07
     bau
    -0.07
     fucking
    -0.07
     парк
    -0.07
     دفع
    -0.07
    POSITIVE LOGITS
     Kontakte
    0.09
     khona
    0.08
     aparece
    0.08
    ，因此
    0.08
    ылатын
    0.07
     instructed
    0.07
    occ
    0.07
     apparition
    0.07
     આવેલી
    0.07
    ，所以
    0.07
    Act Density 0.068%

    No Known Activations