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

    Neuronpedia

    INDEX
    Explanations

    training, research, audio, and descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     شيء
    0.76
    everything
    0.69
    Things
    0.68
     อะไร
    0.68
     mooie
    0.67
    Everything
    0.66
     cosas
    0.65
     ใคร
    0.65
     вещи
    0.65
    อะไร
    0.65
    POSITIVE LOGITS
     arbitrarily
    0.84
     highly
    0.78
     moderately
    0.77
     asynchronously
    0.75
     realistically
    0.74
     naturally
    0.74
     heterogeneous
    0.73
     recursively
    0.72
     accurately
    0.70
     arbitrary
    0.70
    Act Density 0.106%

    No Known Activations