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

    Neuronpedia

    INDEX
    Explanations

    impl

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _WEB
    -0.09
     ebay
    -0.07
     pcb
    -0.07
     телеф
    -0.07
     internet
    -0.07
     eighth
    -0.07
    FileName
    -0.07
    棒
    -0.07
    aggregate
    -0.07
    .unique
    -0.07
    POSITIVE LOGITS
    ality
    0.07
    産
    0.07
    �
    0.07
     дол
    0.07
     השל
    0.07
    办实事
    0.07
     Ritual
    0.07
    寺
    0.06
    したもの
    0.06
    Invest
    0.06
    Act Density 0.004%

    No Known Activations