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

    Neuronpedia

    INDEX
    Explanations

    to or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    리를
    -0.07
     weighs
    -0.06
     Michaels
    -0.06
    drink
    -0.06
     أك
    -0.06
     carbon
    -0.06
     Willow
    -0.06
     الي
    -0.06
     Hoffman
    -0.06
    uddle
    -0.06
    POSITIVE LOGITS
    legation
    0.06
    CLIENT
    0.06
    642
    0.06
    ,proto
    0.06
    _basic
    0.06
     loot
    0.06
    独
    0.06
    components
    0.06
    _flg
    0.06
     cx
    0.06
    Act Density 0.003%

    No Known Activations