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

    Neuronpedia

    INDEX
    Explanations

    indicators of educational progress and grade levels

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    school grades and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.50
    ActionCreators
    -0.39
    utilisons
    -0.38
     krá
    -0.37
     jspb
    -0.36
     vettoriale
    -0.36
    principalColumn
    -0.35
    exploitation
    -0.35
     ब्रेकडाउन
    -0.35
     paille
    -0.35
    POSITIVE LOGITS
     grade
    0.59
     kindergarten
    0.56
     graduating
    0.54
     Kindergarten
    0.52
    Kindergarten
    0.51
     Levels
    0.49
    grade
    0.48
     Grade
    0.47
     grades
    0.47
     HasFactory
    0.46
    Act Density 0.050%

    No Known Activations