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

    Neuronpedia

    INDEX
    Explanations

    studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tela
    -0.08
    ');
↵
↵
    -0.07
     "*"
    -0.07
    .SEVERE
    -0.07
     myList
    -0.07
     مراجع
    -0.07
    าการ
    -0.06
     dataTable
    -0.06
    ujet
    -0.06
     QMap
    -0.06
    POSITIVE LOGITS
     motivating
    0.06
    White
    0.06
    한
    0.06
    ABS
    0.06
    ійно
    0.06
     solves
    0.06
     messaging
    0.06
    ,s
    0.06
    ��
    0.06
    κος
    0.06
    Act Density 0.020%

    No Known Activations