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

    Neuronpedia

    INDEX
    Explanations

    model

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     currentPosition
    -0.08
    麻
    -0.07
     Provided
    -0.07
    operation
    -0.07
    panic
    -0.07
     loves
    -0.07
     rocking
    -0.07
     stripper
    -0.07
    泊
    -0.07
    -move
    -0.07
    POSITIVE LOGITS
     لأنه
    0.07
    企业的
    0.07
    女友
    0.07
     agr
    0.07
    年轻人
    0.07
    릏
    0.07
    (this
    0.06
     gử
    0.06
    >y
    0.06
    agr
    0.06
    Act Density 0.095%

    No Known Activations