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

    Neuronpedia

    INDEX
    Explanations

    flags, writing, peace, chains, airplanes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Style
    0.43
     Pink
    0.43
     Textile
    0.39
     TCE
    0.39
     Class
    0.38
     wil
    0.38
     Tier
    0.38
     yle
    0.38
     pink
    0.37
     all
    0.37
    POSITIVE LOGITS
    ‍
    1.13
    ️
    1.03
    ︎
    0.84
     ‍
    0.78
    ‍♂️
    0.76
    ‌
    0.70
    ‍♀️
    0.70
    ‍♂
    0.69
    󠁧
    0.69
    ‍♀
    0.63
    Act Density 0.007%

    No Known Activations