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

    Neuronpedia

    INDEX
    Explanations

    ensemble

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cocoa
    -0.07
    CHECK
    -0.06
    "*
    -0.06
     ".",
    -0.06
     spaceship
    -0.06
     gpointer
    -0.06
    Marker
    -0.06
     image
    -0.06
    ่าการ
    -0.06
    _WATCH
    -0.06
    POSITIVE LOGITS
     consort
    0.08
     consortium
    0.08
     assortment
    0.08
     Trilogy
    0.07
    续
    0.07
     อำเภ
    0.07
    争
    0.07
    Unique
    0.07
    �
    0.07
     series
    0.06
    Act Density 0.007%

    No Known Activations