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

    Neuronpedia

    INDEX
    Explanations

    Product descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oversized
    -0.07
    ][
    -0.07
    ?>">↵
    -0.07
     TSR
    -0.06
     많
    -0.06
    _inc
    -0.06
     chậm
    -0.06
    ETER
    -0.06
     backlog
    -0.06
     repr
    -0.06
    POSITIVE LOGITS
     Ish
    0.07
    Kay
    0.06
    Posts
    0.06
    DUCT
    0.06
     VOC
    0.06
    yles
    0.06
     zdravot
    0.06
     ryb
    0.06
     Favorites
    0.06
     กรกฎ
    0.06
    Act Density 0.007%

    No Known Activations