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

    Neuronpedia

    INDEX
    Explanations

    role

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     日期
    -0.07
    /t
    -0.07
    restrial
    -0.07
     آب
    -0.07
     dragon
    -0.06
     الرو
    -0.06
    がお
    -0.06
    .INVALID
    -0.06
    -Ch
    -0.06
    :-------------</
    -0.06
    POSITIVE LOGITS
     les
    0.07
    ico
    0.06
    ________________________________
    0.06
    (typ
    0.06
     sene
    0.06
    Join
    0.06
     giành
    0.06
    hya
    0.06
     khoản
    0.06
     commencement
    0.06
    Act Density 0.007%

    No Known Activations