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

    Neuronpedia

    INDEX
    Explanations

    punctuation/const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    胞
    -0.08
     منزل
    -0.08
     dł
    -0.08
     furnish
    -0.07
     telefon
    -0.07
     dancer
    -0.07
    비용
    -0.07
    intendent
    -0.07
    tablename
    -0.07
    턔
    -0.07
    POSITIVE LOGITS
    怒
    0.07
    刃
    0.07
     kaum
    0.07
    [data
    0.07
    ﭶ
    0.06
     >
    0.06
    amic
    0.06
    ὅ
    0.06
    钥
    0.06
    נס
    0.06
    Act Density 0.057%

    No Known Activations