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

    Neuronpedia

    INDEX
    Explanations

    Institutional framework

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (arg
    -0.07
    Worker
    -0.07
    ueil
    -0.07
     tối
    -0.07
     finanzi
    -0.06
     jugg
    -0.06
     Yosh
    -0.06
    _ARGUMENT
    -0.06
     Gives
    -0.06
    '=>
    -0.06
    POSITIVE LOGITS
     Серед
    0.07
    environments
    0.06
    cek
    0.06
    confirmed
    0.06
    dated
    0.06
     nebyl
    0.06
    	ts
    0.06
    Accent
    0.05
     obligatory
    0.05
    iterated
    0.05
    Act Density 0.019%

    No Known Activations