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

    Neuronpedia

    INDEX
    Explanations

    14

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    y
    -0.07
    _SY
    -0.06
     fy
    -0.06
     Number
    -0.06
     tř
    -0.06
    .gz
    -0.06
    	url
    -0.06
    _truth
    -0.06
     templates
    -0.06
     hunted
    -0.06
    POSITIVE LOGITS
     Daniels
    0.07
    ))]↵
    0.07
     �
    0.07
    �
    0.07
    NOW
    0.07
     　　
    0.07
     akan
    0.06
     Manning
    0.06
    _signed
    0.06
     _↵↵
    0.06
    Act Density 0.059%

    No Known Activations