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

    Neuronpedia

    INDEX
    Explanations

    code and programming

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    仙境
    -0.07
    ⼊
    -0.07
     angel
    -0.06
    再见
    -0.06
     EXIT
    -0.06
     als
    -0.06
    _units
    -0.06
    /*================================================================
    -0.06
     Disqus
    -0.06
     Shoes
    -0.06
    POSITIVE LOGITS
     CSP
    0.08
     wildfire
    0.07
    	On
    0.07
     başar
    0.07
    بلاغ
    0.07
    县级
    0.07
     Fire
    0.06
    不具备
    0.06
     חייב
    0.06
     fiss
    0.06
    Act Density 0.158%

    No Known Activations