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

    Neuronpedia

    INDEX
    Explanations

    random sampling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (\$
    -0.07
    (IS
    -0.06
    ya
    -0.06
    Yet
    -0.06
     VIC
    -0.06
    िच
    -0.06
    ו�
    -0.06
    �
    -0.06
    ़ी
    -0.06
    inch
    -0.06
    POSITIVE LOGITS
     Shopify
    0.07
     './
    0.07
    _neurons
    0.06
     kred
    0.06
    -scal
    0.06
    LERİ
    0.06
    ("${
    0.06
    ılığ
    0.06
     plais
    0.06
    症
    0.06
    Act Density 0.005%

    No Known Activations