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

    Neuronpedia

    INDEX
    Explanations

    supervision and guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     insensitive
    0.46
     εἰ
    0.45
     contribute
    0.42
    本当に
    0.41
     ignore
    0.40
    忍
    0.40
     guess
    0.40
     contributes
    0.40
     guessing
    0.39
     góp
    0.39
    POSITIVE LOGITS
     supervision
    1.14
     Supervision
    1.05
     supervised
    1.04
     supervise
    0.96
     supervis
    0.94
    supervised
    0.92
     supervising
    0.90
     Supervis
    0.85
    监督
    0.77
     chaperone
    0.76
    Act Density 0.040%

    No Known Activations