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

    Neuronpedia

    INDEX
    Explanations

    folder

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     staveb
    -0.07
    .US
    -0.07
    ({
↵
    -0.07
     getMax
    -0.06
    (**
    -0.06
    掛
    -0.06
     Highly
    -0.06
     Pasta
    -0.06
     Timeout
    -0.06
     Transformer
    -0.06
    POSITIVE LOGITS
     ド
    0.06
    ư
    0.06
    $tmp
    0.06
     \"{
    0.06
    oking
    0.06
    основ
    0.06
    _LSB
    0.06
     опер
    0.06
    765
    0.06
    ักท
    0.06
    Act Density 0.001%

    No Known Activations