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

    Neuronpedia

    INDEX
    Explanations

    passing grade or score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sizing
    0.44
    sizing
    0.40
     Layers
    0.39
    iyaki
    0.39
     cotidian
    0.38
    ued
    0.38
     세제곱
    0.37
     imaged
    0.37
     layers
    0.37
     layered
    0.37
    POSITIVE LOGITS
     score
    1.82
     grades
    1.76
     scores
    1.71
    成绩
    1.62
    score
    1.59
    Score
    1.53
    scores
    1.53
     Score
    1.52
     Scores
    1.51
     grade
    1.49
    Act Density 0.058%

    No Known Activations