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

    Neuronpedia

    INDEX
    Explanations

    Lombardi/Lombardo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     рабо
    -0.07
     Stap
    -0.06
    arrow
    -0.06
     кус
    -0.06
    ')),↵
    -0.06
    ाश
    -0.06
    ultip
    -0.06
    =='
    -0.06
    senal
    -0.06
    ############
    -0.06
    POSITIVE LOGITS
    .setItems
    0.07
     accred
    0.06
    Ξ
    0.06
     merk
    0.06
     검
    0.06
    Station
    0.06
     Physicians
    0.06
     sexy
    0.06
     všem
    0.06
    _COMP
    0.06
    Act Density 0.001%

    No Known Activations