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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by 's'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    irection
    0.53
    До
    0.51
    used
    0.50
    સ
    0.50
    При
    0.49
    Hace
    0.49
    но
    0.49
    ie
    0.49
    mt
    0.49
    ilinear
    0.49
    POSITIVE LOGITS
     fundamentally
    0.68
     profoundly
    0.67
     strikingly
    0.66
     undeniably
    0.64
     Medicare
    0.62
     WWE
    0.62
     jurispr
    0.62
     modernist
    0.62
     revolutionized
    0.62
     인간
    0.61
    Act Density 0.334%

    No Known Activations