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

    Neuronpedia

    INDEX
    Explanations

    Describing objects or concepts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﺍ
    -0.07
    庹
    -0.07
     :</
    -0.07
    cheon
    -0.07
     Vic
    -0.07
    ОН
    -0.07
    팥
    -0.06
     UNION
    -0.06
     *,
    -0.06
    פייס
    -0.06
    POSITIVE LOGITS
    _POST
    0.07
    crast
    0.07
    	word
    0.07
     embry
    0.07
    .words
    0.06
    (socket
    0.06
     pray
    0.06
    -fr
    0.06
     ammon
    0.06
    攻擊
    0.06
    Act Density 0.214%

    No Known Activations