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

    Neuronpedia

    INDEX
    Explanations

    primary key identifier definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    vad
    0.44
    Ken
    0.42
    Gab
    0.40
    桡
    0.39
    Lay
    0.39
    валася
    0.38
    canceled
    0.38
    ührung
    0.37
    andled
    0.37
    澈
    0.37
    POSITIVE LOGITS
     Id
    0.52
     इद
    0.46
    Id
    0.45
     Idris
    0.45
     id
    0.44
     ID
    0.41
    Ids
    0.41
     Latino
    0.40
     IDs
    0.39
     ata
    0.38
    Act Density 0.001%

    No Known Activations