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
     surprising
    -0.07
     تای
    -0.07
    行动
    -0.07
     eskorte
    -0.07
    _Collections
    -0.06
    seo
    -0.06
    ivy
    -0.06
    isiert
    -0.06
    ("~
    -0.06
     Wrestling
    -0.06
    POSITIVE LOGITS
     Pry
    0.06
     chooser
    0.06
    _pp
    0.06
    σαν
    0.06
     pard
    0.06
    igin
    0.06
    lásil
    0.06
     DI
    0.06
    .precision
    0.05
    ...↵↵↵↵
    0.05
    Act Density 0.028%

    No Known Activations