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

    Neuronpedia

    INDEX
    Explanations

    begun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Style
    -0.07
    외
    -0.06
    Patrick
    -0.06
    -handler
    -0.06
    igInteger
    -0.06
    _travel
    -0.06
    .My
    -0.06
     democrat
    -0.06
     Segment
    -0.06
    ículos
    -0.06
    POSITIVE LOGITS
     begun
    0.30
     gotten
    0.08
     embarked
    0.08
     Swarm
    0.07
     Breitbart
    0.07
     AudioSource
    0.07
     zw
    0.07
     موتور
    0.07
    hone
    0.07
     Grammar
    0.07
    Act Density 0.002%

    No Known Activations