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

    Neuronpedia

    INDEX
    Explanations

    Trading platforms/algorithms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     smarter
    -0.08
     Laugh
    -0.08
     suchen
    -0.07
     rendre
    -0.07
    <Document
    -0.07
    .twimg
    -0.07
    跑道
    -0.07
     телефон
    -0.07
    開放
    -0.07
     getColumn
    -0.07
    POSITIVE LOGITS
    guards
    0.07
     inexp
    0.07
    {}_
    0.07
    ensburg
    0.07
    -free
    0.07
     ERR
    0.07
     manip
    0.06
     ENUM
    0.06
    プロ
    0.06
    unix
    0.06
    Act Density 0.002%

    No Known Activations