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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    userService
    -0.08
    ımın
    -0.07
     premise
    -0.06
    -blood
    -0.06
     müm
    -0.06
    илася
    -0.06
     Soul
    -0.06
    	define
    -0.06
    -talk
    -0.06
    .Since
    -0.06
    POSITIVE LOGITS
     it
    0.11
     them
    0.07
    Activated
    0.07
     It
    0.07
    лиц
    0.07
    وا
    0.07
    ِ
    0.06
    ty
    0.06
    龄
    0.06
    BIT
    0.06
    Act Density 0.130%

    No Known Activations