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

    Neuronpedia

    INDEX
    Explanations

    departments and divisions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bern
    0.53
    fels
    0.46
    ค
    0.45
    his
    0.43
     obeys
    0.42
    horses
    0.42
    ieh
    0.42
     Sawyer
    0.42
    pcion
    0.41
    murder
    0.40
    POSITIVE LOGITS
     اتحاد
    0.52
     antibody
    0.49
     পাইল
    0.48
    IERC
    0.48
     stalwart
    0.48
    "+
    0.47
    +{
    0.47
     cytok
    0.47
    ILITY
    0.46
     influent
    0.46
    Act Density 0.008%

    No Known Activations