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

    Neuronpedia

    INDEX
    Explanations

    URL query parameters and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    miš
    0.67
    🅱
    0.67
     alve
    0.65
    ịt
    0.65
     dah
    0.65
     కరో
    0.64
     hơi
    0.63
    कप्तान
    0.63
     darunter
    0.62
    祟
    0.61
    POSITIVE LOGITS
    &
    3.89
     &
    3.58
    ]&
    2.93
    &\
    2.92
    }&
    2.87
    )&
    2.80
    &$
    2.74
     &\
    2.64
     &,
    2.64
    ＆
    2.64
    Act Density 0.113%

    No Known Activations