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

    Neuronpedia

    INDEX
    Explanations

    interfaces and connections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⍨
    -0.07
     flavorful
    -0.07
     dismissed
    -0.07
    /(
    -0.07
    선
    -0.06
    弥漫
    -0.06
    �
    -0.06
    小学
    -0.06
     kích
    -0.06
    灌
    -0.06
    POSITIVE LOGITS
     participation
    0.07
     ?>
↵
    0.07
    etak
    0.07
     quotas
    0.07
    ậ
    0.07
    ovel
    0.07
     DeepCopy
    0.07
    잴
    0.06
    rtl
    0.06
    몫
    0.06
    Act Density 0.061%

    No Known Activations