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

    Neuronpedia

    INDEX
    Explanations

    mojo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ्गत
    -0.07
    Thanks
    -0.07
    (lua
    -0.06
    bast
    -0.06
    Fortunately
    -0.06
    碎
    -0.06
    	DD
    -0.06
     Wax
    -0.06
    _MULT
    -0.06
     NJ
    -0.06
    POSITIVE LOGITS
     Lawyer
    0.07
    اسات
    0.06
    appointed
    0.06
    ğan
    0.06
     "]
    0.06
    [SerializeField
    0.06
     dahi
    0.06
    ?-
    0.06
    UMMY
    0.06
    資料
    0.06
    Act Density 0.000%

    No Known Activations