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

    Neuronpedia

    INDEX
    Explanations

    def

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     العربية
    -0.07
    理念
    -0.07
    ր
    -0.07
    Executor
    -0.07
    fel
    -0.07
    .Physics
    -0.07
    scope
    -0.07
    htt
    -0.07
     wrest
    -0.07
    reck
    -0.06
    POSITIVE LOGITS
     dummy
    0.07
    옆
    0.07
    开关
    0.07
     mesa
    0.07
    社交
    0.07
    InOut
    0.07
     MYSQL
    0.07
    ┷
    0.06
     jpg
    0.06
    英国
    0.06
    Act Density 0.010%

    No Known Activations