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

    Neuronpedia

    INDEX
    Explanations

    purpose, target, or decision

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maravill
    0.42
     rationalize
    0.40
    澈
    0.40
    樂
    0.39
    更大
    0.39
     అయినా
    0.39
     marvellous
    0.38
     】,
    0.38
    ၷ
    0.38
     subsection
    0.38
    POSITIVE LOGITS
    γο
    0.49
    тів
    0.48
    ત્તા
    0.48
     формы
    0.47
    bury
    0.47
    с
    0.46
    ية
    0.45
    inių
    0.45
    ҳои
    0.45
    ंसाठी
    0.45
    Act Density 0.000%

    No Known Activations