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

    Neuronpedia

    INDEX
    Explanations

    Mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deleting
    -0.08
     пл
    -0.07
     сг
    -0.07
     ಸರ
    -0.07
     chapters
    -0.07
     Stel
    -0.07
    ler
    -0.06
    ")↵//
    -0.06
     reorgan
    -0.06
    頁
    -0.06
    POSITIVE LOGITS
     miteinander
    0.09
    werte
    0.08
    activo
    0.08
    	values
    0.08
     values
    0.08
    (vals
    0.08
     capitalization
    0.08
     নিজেদের
    0.08
     değer
    0.08
     cruelty
    0.08
    Act Density 0.052%

    No Known Activations