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

    Neuronpedia

    INDEX
    Explanations

    touchdown

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    职业技能
    -0.07
    ValueGenerationStrategy
    -0.07
    cest
    -0.07
    🥊
    -0.07
    _mc
    -0.07
    _cli
    -0.07
    pire
    -0.07
    랴
    -0.07
    чь
    -0.07
     Part
    -0.07
    POSITIVE LOGITS
    [cnt
    0.07
    .findAll
    0.07
     Deadly
    0.07
    Philadelphia
    0.07
    ]){↵
    0.07
    marca
    0.07
    通知书
    0.07
     широко
    0.06
    AZY
    0.06
     dead
    0.06
    Act Density 0.001%

    No Known Activations