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

    Neuronpedia

    INDEX
    Explanations

    dialogue with character names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    娼
    0.48
     adultery
    0.48
     Pavlov
    0.45
     печа
    0.45
     nuns
    0.45
     Kwiat
    0.45
     policewomen
    0.43
    媾
    0.43
     Bapak
    0.43
     женщи
    0.42
    POSITIVE LOGITS
     Erie
    0.49
     athlet
    0.45
     টাইগার
    0.45
     sporting
    0.45
     Roswell
    0.44
    伥
    0.44
     ج
    0.44
     Chromebook
    0.43
     collectively
    0.43
     laser
    0.43
    Act Density 0.004%

    No Known Activations