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

    Neuronpedia

    INDEX
    Explanations

    places and descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BigDecimal
    0.35
     immutable
    0.35
    nommen
    0.35
     demokrat
    0.34
     voidaan
    0.32
     Taxonomic
    0.32
     bson
    0.31
     Riemannian
    0.31
     Skyrim
    0.31
     Variability
    0.30
    POSITIVE LOGITS
    V
    0.45
    P
    0.42
    U
    0.42
    G
    0.42
    R
    0.41
    III
    0.40
    B
    0.40
    S
    0.38
    N
    0.38
    D
    0.38
    Act Density 0.051%

    No Known Activations