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

    Neuronpedia

    INDEX
    Explanations

    Ot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Shemale
    -0.06
    foo
    -0.06
    论坛
    -0.06
    );;↵
    -0.06
     ハ
    -0.06
     商品
    -0.06
     dictionaries
    -0.06
     pprint
    -0.05
    (po
    -0.05
    |}↵
    -0.05
    POSITIVE LOGITS
     IOException
    0.08
     якого
    0.07
     zel
    0.07
    :'',
    0.07
    .Call
    0.07
     Ab
    0.07
    lte
    0.06
     toll
    0.06
    ellipse
    0.06
     jest
    0.06
    Act Density 0.003%

    No Known Activations