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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     section
    -0.07
     padding
    -0.07
    (/^\
    -0.07
    pack
    -0.07
    (end
    -0.06
    	padding
    -0.06
    説明
    -0.06
    _indicator
    -0.06
     commas
    -0.06
    (labels
    -0.06
    POSITIVE LOGITS
     onstage
    0.07
    _DUMP
    0.06
    SKTOP
    0.06
    /shop
    0.06
     ulož
    0.06
     nons
    0.06
     influencing
    0.06
    Welcome
    0.06
     mak
    0.06
    AGER
    0.06
    Act Density 0.004%

    No Known Activations