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

    Neuronpedia

    INDEX
    Explanations

    scientific papers and entertainment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smrt
    -0.07
     köz
    -0.06
    �
    -0.06
     Yas
    -0.06
     compr
    -0.06
    placement
    -0.06
     lazy
    -0.06
     Trash
    -0.06
    stí
    -0.06
     Islam
    -0.06
    POSITIVE LOGITS
    specified
    0.07
    atte
    0.07
    Listener
    0.07
    _dic
    0.06
    accounts
    0.06
     ARGS
    0.06
     continues
    0.06
    However
    0.06
     Renew
    0.06
     delicious
    0.06
    Act Density 0.001%

    No Known Activations