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

    Neuronpedia

    INDEX
    Explanations

    large quantities or long lengths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    érist
    0.68
     веществ
    0.56
     کننده
    0.54
    odet
    0.54
    نوع
    0.53
    Stylesheet
    0.53
    acyj
    0.52
    Compatibility
    0.51
    Database
    0.50
    Properties
    0.50
    POSITIVE LOGITS
    超过
    1.23
     large
    1.20
     larger
    1.11
     length
    1.07
     exceed
    1.05
     longer
    1.04
     більше
    1.00
     дли
    1.00
    超過
    1.00
     lunghezza
    1.00
    Act Density 0.026%

    No Known Activations