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

    Neuronpedia

    INDEX
    Explanations

    POST

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     extensive
    -0.07
    (to
    -0.06
    器具
    -0.06
     diagnosis
    -0.06
    -single
    -0.06
     besides
    -0.06
    DAQ
    -0.06
     Fine
    -0.06
     scaling
    -0.06
     Inspector
    -0.06
    POSITIVE LOGITS
    J
    0.07
     môn
    0.07
    ในการ
    0.07
     ############################################################################
    0.07
     ?>>
    0.06
    hawk
    0.06
    ㋡
    0.06
    _days
    0.06
    就没有
    0.06
    �
    0.06
    Act Density 0.171%

    No Known Activations