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

    Neuronpedia

    INDEX
    Explanations

    Cartoon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     사진
    -0.07
     съ
    -0.07
    mi
    -0.06
    事
    -0.06
    Army
    -0.06
    Token
    -0.06
    олот
    -0.06
     snap
    -0.06
    뮤
    -0.06
    embrance
    -0.06
    POSITIVE LOGITS
    �
    0.07
     elected
    0.06
     Bened
    0.06
    _BUS
    0.06
     connects
    0.06
     MAY
    0.06
    IFEST
    0.06
    abilecek
    0.06
    oard
    0.06
     नए
    0.06
    Act Density 0.084%

    No Known Activations