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

    Neuronpedia

    INDEX
    Explanations

    catalog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Highlights
    -0.08
    mi
    -0.07
     정부
    -0.07
    anlı
    -0.07
    .CENTER
    -0.07
     headlines
    -0.06
     стандарт
    -0.06
     Yankee
    -0.06
     restarted
    -0.06
    reme
    -0.06
    POSITIVE LOGITS
    τικο
    0.07
     Львів
    0.06
    ++];↵
    0.06
     """.
    0.06
     lan
    0.06
    '),↵↵
    0.06
    _CF
    0.06
     //*
    0.06
    .matcher
    0.06
     Atmospheric
    0.06
    Act Density 0.003%

    No Known Activations