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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utches
    -0.09
     implanted
    -0.08
    temporary
    -0.08
    ogenerated
    -0.08
     inspected
    -0.08
     гум
    -0.07
    ém
    -0.07
     одному
    -0.07
    cassert
    -0.07
     Grenzen
    -0.07
    POSITIVE LOGITS
     angegeben
    0.09
     afin
    0.09
    Youtube
    0.08
    Optional
    0.08
     지정
    0.08
     acara
    0.08
     asign
    0.07
    ימ
    0.07
     bilgi
    0.07
     olay
    0.07
    Act Density 0.001%

    No Known Activations