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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Arn
    -0.07
    าระ
    -0.06
     homers
    -0.06
     beating
    -0.06
    76
    -0.06
     ні
    -0.06
    حد
    -0.06
     Ideally
    -0.06
     NP
    -0.06
    .Re
    -0.06
    POSITIVE LOGITS
    Fuck
    0.07
    ogue
    0.06
    教育
    0.06
     supportive
    0.06
    اقتص
    0.06
     Fashion
    0.06
    	Object
    0.06
     Fuck
    0.06
     verilen
    0.06
    iture
    0.06
    Act Density 0.002%

    No Known Activations