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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pens
    -0.07
     exhib
    -0.06
    	Render
    -0.06
     Badge
    -0.06
    (pred
    -0.06
    Photos
    -0.06
     blindly
    -0.06
    Guard
    -0.06
    ibe
    -0.06
     Weld
    -0.06
    POSITIVE LOGITS
    ฐาน
    0.07
    ์ต
    0.07
     확실
    0.06
    criminal
    0.06
    _Reset
    0.06
     Goodman
    0.06
     getSupportFragmentManager
    0.06
     fearful
    0.06
    .flatMap
    0.06
    /view
    0.06
    Act Density 0.006%

    No Known Activations