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

    Neuronpedia

    INDEX
    Explanations

    technical topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lazy
    -0.07
    КИ
    -0.06
     destroying
    -0.06
    _POST
    -0.06
    .Post
    -0.06
    ACCOUNT
    -0.06
    ovanou
    -0.06
    ті
    -0.06
    ASK
    -0.06
     Throws
    -0.06
    POSITIVE LOGITS
    849
    0.07
     Lon
    0.07
    ieurs
    0.07
    	find
    0.07
     bonne
    0.07
     axle
    0.06
     uninsured
    0.06
    못
    0.06
     صن
    0.06
     utc
    0.06
    Act Density 0.053%

    No Known Activations