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

    Neuronpedia

    INDEX
    Explanations

    tape datasets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stories
    0.81
     stories
    0.78
     sobą
    0.75
    Weblinks
    0.74
    шений
    0.70
     অবিশ্বাস
    0.70
     anecd
    0.69
     storie
    0.69
    дів
    0.69
    льм
    0.68
    POSITIVE LOGITS
     their
    0.73
     mess
    0.67
    𝗍
    0.65
     peninsula
    0.65
     recess
    0.63
     Mavericks
    0.62
     cleaning
    0.62
    ery
    0.61
     cleanup
    0.61
     beaker
    0.60
    Act Density 0.000%

    No Known Activations