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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Entities
    -0.07
    currentUser
    -0.07
     collabor
    -0.07
     REGION
    -0.06
    .sex
    -0.06
    .getLocation
    -0.06
     menacing
    -0.06
     至
    -0.06
    MH
    -0.06
    Navigator
    -0.06
    POSITIVE LOGITS
    ]])↵↵
    0.06
     brides
    0.06
    ンディ
    0.06
    .runners
    0.06
    πο
    0.06
     Subscribe
    0.06
    kiye
    0.06
     â
    0.06
    于是
    0.06
    etler
    0.06
    Act Density 0.011%

    No Known Activations