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

    Neuronpedia

    INDEX
    Explanations

    younger people or consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rai
    0.41
     Eich
    0.40
     Smyth
    0.40
     cup
    0.39
     Morgan
    0.38
     offline
    0.38
     vía
    0.38
     Ebene
    0.38
     N
    0.38
     Aj
    0.37
    POSITIVE LOGITS
    entingan
    0.42
    銷
    0.41
     இளம்
    0.40
    STRACT
    0.39
    ilerinin
    0.39
    ナトリ
    0.39
    неоп
    0.38
    jectories
    0.38
    expects
    0.38
    curricular
    0.38
    Act Density 0.001%

    No Known Activations