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
    侹
    -0.07
    .scope
    -0.07
    cec
    -0.07
    capitalize
    -0.06
    xee
    -0.06
    gross
    -0.06
     clumsy
    -0.06
     ###
    -0.06
     José
    -0.06
    .Try
    -0.06
    POSITIVE LOGITS
     drinks
    0.08
     questioned
    0.07
     uchar
    0.07
    uttle
    0.07
     schedules
    0.07
    �
    0.07
    安娜
    0.07
     states
    0.07
     Virginia
    0.07
     Atlanta
    0.07
    Act Density 0.001%

    No Known Activations