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

    Neuronpedia

    INDEX
    Explanations

    ure

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ดา
    -0.07
     GPI
    -0.07
    得知
    -0.07
    lli
    -0.07
     lsp
    -0.07
    落地
    -0.07
     datingside
    -0.06
    ”.
    -0.06
    大赛
    -0.06
    =").
    -0.06
    POSITIVE LOGITS
    medical
    0.07
     flavors
    0.07
     meat
    0.07
    cancelled
    0.07
    encoder
    0.07
    balanced
    0.07
    厦门
    0.07
    Cleaning
    0.07
    .module
    0.07
    userManager
    0.07
    Act Density 0.001%

    No Known Activations