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

    Neuronpedia

    INDEX
    Explanations

    Team alignment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eu
    -0.08
     FTP
    -0.08
    stitute
    -0.07
    bitrary
    -0.07
     unethical
    -0.07
    итайте
    -0.07
     zdr
    -0.07
    APA
    -0.07
     SLOT
    -0.07
    .net
    -0.07
    POSITIVE LOGITS
     அனைவர
    0.13
     الجميع
    0.13
     stakeholders
    0.13
    理解
    0.13
     이해
    0.12
     understands
    0.12
     সবাই
    0.12
     everyone
    0.12
    团队
    0.11
     herkes
    0.11
    Act Density 0.020%

    No Known Activations