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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    CACHE
    -0.07
    aida
    -0.07
     nebezpeč
    -0.07
    벤트
    -0.07
     نیر
    -0.06
    乎
    -0.06
    δας
    -0.06
    cran
    -0.06
    emu
    -0.06
    anche
    -0.06
    POSITIVE LOGITS
     boots
    0.07
    _cate
    0.06
     bson
    0.06
     نتایج
    0.06
     счет
    0.06
     Brewers
    0.06
     probe
    0.06
    	data
    0.06
     شاه
    0.06
     sleeve
    0.06
    Act Density 0.001%

    No Known Activations