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

    Neuronpedia

    INDEX
    Explanations

    compound parts of speech

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -1.28
     rurales
    -1.25
     frança
    -1.24
     baterie
    -1.21
     pouvons
    -1.20
     camisas
    -1.18
    ภัณฑ์
    -1.18
     the
    -1.17
    gün
    -1.16
     cerâmica
    -1.15
    POSITIVE LOGITS
    N
    1.41
    _
    1.36
    T
    1.26
    M
    1.23
    For
    1.20
     T
    1.19
    L
    1.16
    t
    1.14
    In
    1.13
    With
    1.13
    Act Density 0.010%

    No Known Activations