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

    Neuronpedia

    INDEX
    Explanations

    IDs and labels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lapsed
    0.37
     gole
    0.36
     BOU
    0.35
     treated
    0.35
     lapse
    0.34
    使
    0.34
    ᱹ
    0.34
    voer
    0.34
     trái
    0.34
    لاص
    0.33
    POSITIVE LOGITS
    １
    0.49
    uuid
    0.47
     ۱
    0.45
    eqref
    0.45
     urn
    0.44
    1
    0.43
     uuid
    0.43
     getId
    0.43
    MDEwOlJlcG
    0.42
    gmail
    0.42
    Act Density 0.008%

    No Known Activations