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

    Neuronpedia

    INDEX
    Explanations

    cleaning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ISTRATION
    -0.07
     jeszcze
    -0.07
    慢慢的
    -0.07
    督促
    -0.07
    иг
    -0.07
    ㉥
    -0.07
     بغ
    -0.06
    真的
    -0.06
    专心
    -0.06
    ạy
    -0.06
    POSITIVE LOGITS
     lamp
    0.07
     nominal
    0.07
    Among
    0.07
     Atl
    0.07
    book
    0.07
     drop
    0.07
    enderit
    0.07
     Ripple
    0.06
    basic
    0.06
     Authorized
    0.06
    Act Density 0.013%

    No Known Activations