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

    Neuronpedia

    INDEX
    Explanations

    News reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     oath
    -0.07
    鹭
    -0.07
    nicos
    -0.07
     Sitting
    -0.07
     rodents
    -0.07
    ifornia
    -0.07
    �
    -0.07
    Haunted
    -0.06
     وهنا
    -0.06
    蹽
    -0.06
    POSITIVE LOGITS
    可能发生
    0.07
    Encryption
    0.07
    (',')↵
    0.07
    .Infof
    0.07
    .Debugf
    0.07
    ෆ
    0.07
    شن
    0.07
    -Jan
    0.07
    分别是
    0.06
    Override
    0.06
    Act Density 0.081%

    No Known Activations