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

    Neuronpedia

    INDEX
    Explanations

    mer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UNET
    -0.06
    fu
    -0.06
     conta
    -0.06
    ujícím
    -0.06
     شیمی
    -0.06
    ”,
    -0.06
    Spoiler
    -0.06
     Qualified
    -0.06
     disco
    -0.06
     Thu
    -0.06
    POSITIVE LOGITS
    	contentPane
    0.07
    째
    0.07
     křes
    0.07
    讲
    0.06
    XMLLoader
    0.06
    müş
    0.06
    getStatusCode
    0.06
    _RGCTX
    0.06
     сом
    0.06
    ReadOnly
    0.06
    Act Density 0.002%

    No Known Activations