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

    Neuronpedia

    INDEX
    Explanations

    code/data strings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     đêm
    -0.07
    udem
    -0.07
    ຫ
    -0.07
    десь
    -0.07
    ếu
    -0.07
     paycheck
    -0.06
     "{\"
    -0.06
    ယ
    -0.06
    新开
    -0.06
    过大
    -0.06
    POSITIVE LOGITS
    zilla
    0.08
    RE
    0.07
     unilateral
    0.07
     DIG
    0.07
    oring
    0.07
    WARNING
    0.07
     ث
    0.07
     Remove
    0.07
    _COMPILE
    0.06
     العسكري
    0.06
    Act Density 0.081%

    No Known Activations