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

    Neuronpedia

    INDEX
    Explanations

    student year levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    them
    0.46
    াল
    0.44
     person
    0.43
     décadas
    0.43
     yahoo
    0.43
     more
    0.42
     exons
    0.42
    <0xE3>
    0.41
     obtain
    0.41
     federal
    0.41
    POSITIVE LOGITS
     Sophomore
    0.59
     sophomore
    0.59
     මේ
    0.53
    Soph
    0.48
     freshman
    0.45
     సంవత్స
    0.45
     সৌম
    0.45
    በት
    0.45
     ഇപ്പോള്‍
    0.45
     올해
    0.44
    Act Density 0.006%

    No Known Activations