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

    Neuronpedia

    INDEX
    Explanations

    run

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
     ist
    -0.07
    longitude
    -0.07
    委员会
    -0.07
     Wagner
    -0.06
     таблиц
    -0.06
     struck
    -0.06
    450
    -0.06
    ierung
    -0.06
    -Con
    -0.06
    POSITIVE LOGITS
    ffect
    0.07
     تشخیص
    0.07
     Eval
    0.06
     relied
    0.06
     listened
    0.06
     dov
    0.06
     palindrome
    0.06
    _WAIT
    0.06
     enormously
    0.06
     Gins
    0.06
    Act Density 0.028%

    No Known Activations