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

    Neuronpedia

    INDEX
    Explanations

    academic festivals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    data
    0.58
    s
    0.57
    summary
    0.55
    dag
    0.54
    k
    0.54
     en
    0.54
    info
    0.53
    table
    0.53
    ene
    0.52
    dad
    0.52
    POSITIVE LOGITS
    热情
    0.46
     cylinders
    0.46
     фестива
    0.43
     académ
    0.43
     Акаде
    0.43
    жки
    0.43
     училище
    0.43
     распа
    0.42
     ожи
    0.42
     khởi
    0.42
    Act Density 0.000%

    No Known Activations