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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عر
    -0.07
    �
    -0.07
     correspond
    -0.07
    (arguments
    -0.06
    楷
    -0.06
     ह
    -0.06
     velocity
    -0.06
     committed
    -0.06
    ウェ
    -0.06
    十六
    -0.06
    POSITIVE LOGITS
    سكر
    0.09
     studs
    0.08
    มากม
    0.08
    umbn
    0.07
     icons
    0.07
    臜
    0.07
     Beef
    0.07
     Ezra
    0.07
     savedInstanceState
    0.07
    ,Yes
    0.07
    Act Density 0.039%

    No Known Activations