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

    Neuronpedia

    INDEX
    Explanations

    checkout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    \modules
    -0.07
    olta
    -0.07
    ustralia
    -0.06
    usions
    -0.06
    uteč
    -0.06
     erfolgreich
    -0.06
     البر
    -0.06
    surname
    -0.06
    anax
    -0.06
    척
    -0.06
    POSITIVE LOGITS
    惠
    0.07
     угод
    0.06
    fte
    0.06
    StringEncoding
    0.06
     Pelosi
    0.06
     urlString
    0.06
     LOCK
    0.06
     translators
    0.06
    (pic
    0.06
     Blick
    0.06
    Act Density 0.011%

    No Known Activations