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

    Neuronpedia

    INDEX
    Explanations

    par

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    狉
    -0.07
    먕
    -0.07
     nightclub
    -0.07
    בניין
    -0.06
    삑
    -0.06
    ¼
    -0.06
    립
    -0.06
     placing
    -0.06
    _TD
    -0.06
    LLU
    -0.06
    POSITIVE LOGITS
     Aval
    0.08
    怎么能
    0.07
     merg
    0.07
     work
    0.07
     killer
    0.07
     Portug
    0.07
     кап
    0.07
    .filters
    0.07
    plugin
    0.07
     Credits
    0.07
    Act Density 0.001%

    No Known Activations