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

    Neuronpedia

    INDEX
    Explanations

    cooperation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gratuits
    -0.07
    mma
    -0.07
    yll
    -0.07
    🍾
    -0.07
     righteousness
    -0.07
     jer
    -0.07
    献
    -0.07
    を集
    -0.07
    ALLENG
    -0.07
    SEE
    -0.06
    POSITIVE LOGITS
     후
    0.08
    _platform
    0.07
    引来
    0.07
     —
    0.07
     Voc
    0.07
     intern
    0.07
     tầng
    0.07
     البنك
    0.07
    аб
    0.06
    0.06
    Act Density 0.022%

    No Known Activations