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

    Neuronpedia

    INDEX
    Explanations

    scientific names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ichromo
    1.50
    eradish
    1.50
     highlands
    1.46
    hetiti
    1.46
    aditional
    1.46
    addassa
    1.44
    ylinder
    1.44
     вікісторінку
    1.43
    usual
    1.42
     highland
    1.42
    POSITIVE LOGITS
      
    1.05
     Apps
    0.97
     poco
    0.96
     incon
    0.93
     это
    0.92
     הע
    0.92
     app
    0.91
     внимания
    0.90
     I
    0.90
    嚴
    0.89
    Act Density 0.023%

    No Known Activations