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

    Neuronpedia

    INDEX
    Explanations

    numerical data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Peng
    -0.07
     Honestly
    -0.06
     exhibited
    -0.06
    Andy
    -0.06
     motivate
    -0.06
     рамках
    -0.06
     guarantee
    -0.06
     frustrations
    -0.06
    овани
    -0.06
     😉
    -0.06
    POSITIVE LOGITS
     woke
    0.07
    ToLower
    0.07
    麦
    0.07
    =M
    0.07
    ीएस
    0.07
    _fl
    0.06
     Uno
    0.06
    .getClient
    0.06
     bliss
    0.06
    pixels
    0.06
    Act Density 0.010%

    No Known Activations