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

    Neuronpedia

    INDEX
    Explanations

    conda build infrastructure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pixels
    0.50
     pixel
    0.47
     GridPane
    0.45
     Pix
    0.44
     Pixel
    0.43
     caretaker
    0.42
     CTR
    0.41
    pixels
    0.40
     CMR
    0.40
     preacher
    0.40
    POSITIVE LOGITS
    Це
    0.50
     பஞ்ச
    0.49
     expérience
    0.49
    Drugs
    0.48
    ustion
    0.47
    france
    0.47
    erade
    0.47
    בש
    0.46
    óticos
    0.46
    ance
    0.45
    Act Density 0.003%

    No Known Activations