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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    nah
    -0.07
     lottery
    -0.06
    ↵                    ↵
    -0.06
    .parent
    -0.06
    =int
    -0.06
    cle
    -0.06
     Tob
    -0.06
    ้ผ
    -0.06
    mue
    -0.06
    ejs
    -0.06
    POSITIVE LOGITS
    電視
    0.07
    ').'</
    0.07
     samostat
    0.06
    ��이지
    0.06
     блок
    0.06
    _Master
    0.06
     Söz
    0.06
     ACS
    0.06
     Под
    0.06
     pseud
    0.06
    Act Density 0.059%

    No Known Activations