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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Dao
    -0.08
    _mentions
    -0.07
     Rent
    -0.07
     اقتص
    -0.07
     shoe
    -0.07
    럭
    -0.07
     trồng
    -0.07
    ENT
    -0.06
    DOUBLE
    -0.06
    Δ
    -0.06
    POSITIVE LOGITS
    primaryKey
    0.06
    }),
    0.06
     nouvel
    0.06
    (getClass
    0.06
    “你
    0.05
    ']),
    0.05
     maneu
    0.05
     Furthermore
    0.05
    Furthermore
    0.05
    behavior
    0.05
    Act Density 0.007%

    No Known Activations