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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aun
    -0.07
     advertisements
    -0.07
    团
    -0.07
     superficial
    -0.06
    hil
    -0.06
    _ent
    -0.06
     Meng
    -0.06
     lun
    -0.06
    (PARAM
    -0.06
    _IO
    -0.06
    POSITIVE LOGITS
    šku
    0.07
    userName
    0.06
    оду
    0.06
    časí
    0.06
    	include
    0.06
     Reviewed
    0.06
    .raises
    0.06
     Homepage
    0.06
    hetic
    0.06
    -finals
    0.06
    Act Density 0.000%

    No Known Activations