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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     museum
    -0.07
    וצ
    -0.07
    妈妈
    -0.07
    =$(
    -0.07
     cancell
    -0.07
    ่อง
    -0.07
     Maui
    -0.06
    contra
    -0.06
    Distribution
    -0.06
     diploma
    -0.06
    POSITIVE LOGITS
     reluctant
    0.07
     Fixes
    0.07
     sluts
    0.07
    ImplOptions
    0.07
    ísticas
    0.07
    一切都是
    0.07
    "][$
    0.07
    只能
    0.07
     Gus
    0.07
     GameState
    0.07
    Act Density 0.025%

    No Known Activations