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

    Neuronpedia

    INDEX
    Explanations

    the way ASCII art looks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boy
    0.41
     President
    0.40
     president
    0.39
     youngest
    0.39
    p
    0.39
     girl
    0.39
     brainchild
    0.39
     eldest
    0.38
     Two
    0.38
     biggest
    0.38
    POSITIVE LOGITS
     reproducibility
    0.40
     `=`,
    0.40
     обрабо
    0.38
     способы
    0.37
     использования
    0.36
     analyse
    0.36
     обработки
    0.35
     usability
    0.35
     computational
    0.34
     databases
    0.34
    Act Density 0.046%

    No Known Activations