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

    Neuronpedia

    INDEX
    Explanations

    styles and tones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     revolutionized
    0.47
     owned
    0.45
     billions
    0.44
     ecosystems
    0.44
     nossas
    0.42
     microbiology
    0.42
     labs
    0.42
    ^
    0.42
     millions
    0.41
     terminals
    0.41
    POSITIVE LOGITS
     말투
    0.55
     подойдет
    0.54
     подчер
    0.54
     стиль
    0.51
     подход
    0.51
     버전
    0.50
     edgy
    0.49
     варі
    0.49
     версия
    0.48
     Emphasis
    0.48
    Act Density 0.330%

    No Known Activations