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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .or
    -0.07
     clutch
    -0.06
    劃
    -0.06
    .bulk
    -0.06
    �
    -0.06
    تب
    -0.06
    _EXP
    -0.06
    	dir
    -0.06
     фев
    -0.06
    Pager
    -0.06
    POSITIVE LOGITS
     distinguish
    0.06
     unsigned
    0.06
     CWE
    0.06
    (tt
    0.06
    ((_
    0.06
     }),↵
    0.06
     '((
    0.06
     Katy
    0.06
    maid
    0.06
     Observer
    0.06
    Act Density 0.003%

    No Known Activations