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

    Neuronpedia

    INDEX
    Explanations

    libraries

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gordon
    -0.07
    جب
    -0.07
    ивши
    -0.06
    Davis
    -0.06
     Simpson
    -0.06
    _prev
    -0.06
     {}↵↵
    -0.06
     Simulation
    -0.06
     monitored
    -0.06
    $this
    -0.06
    POSITIVE LOGITS
    leş
    0.06
     соот
    0.06
    言った
    0.06
     lyn
    0.06
     дра
    0.06
     Mt
    0.06
    orsch
    0.06
     난
    0.05
     shorten
    0.05
    ulares
    0.05
    Act Density 0.049%

    No Known Activations