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

    Neuronpedia

    INDEX
    Explanations

    appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    clinic
    -0.08
     mindset
    -0.08
    (origin
    -0.07
     परम
    -0.07
    )||
    -0.07
    잠
    -0.07
    (['
    -0.07
     klaus
    -0.07
    ifecycle
    -0.07
    cknowled
    -0.07
    POSITIVE LOGITS
     intimidating
    0.13
     ẹni
    0.12
    似
    0.11
     కనిప
    0.11
     decept
    0.11
    乎
    0.11
     daunting
    0.10
     दिस
    0.10
     মনে
    0.10
     લાગે
    0.10
    Act Density 0.108%

    No Known Activations