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

    Neuronpedia

    INDEX
    Explanations

    text or code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Вайлдберриз
    0.40
    IDAY
    0.39
    🚺
    0.36
    MDEwOlJlcG
    0.36
    👏👏
    0.36
     शिलालेख
    0.36
     добавлен
    0.36
    ពិសេស
    0.36
    📬
    0.36
     größer
    0.35
    POSITIVE LOGITS
     Maestro
    0.34
     homeland
    0.32
    Sincerely
    0.31
     ‘
    0.31
     Make
    0.31
     nghi
    0.31
    レ
    0.31
    노
    0.31
    ‘
    0.30
     Ні
    0.30
    Act Density 0.000%

    No Known Activations