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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -ID
    -0.08
     pilgrimage
    -0.08
    (at
    -0.07
     polyester
    -0.07
     Ekon
    -0.07
    ่ง
    -0.07
    _constraint
    -0.07
     Pv
    -0.07
     QE
    -0.07
     Passport
    -0.07
    POSITIVE LOGITS
     "");↵
    0.06
     '{$
    0.06
    详情
    0.06
    :'↵
    0.06
    ัพ
    0.06
     Hillary
    0.06
    ':↵
    0.06
     '');
    0.06
    '){
    0.06
    Simply
    0.06
    Act Density 0.021%

    No Known Activations