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

    Neuronpedia

    INDEX
    Explanations

    is used in a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etto
    -0.11
    UrlParser
    -0.09
    tru
    -0.09
     rá»ĵi
    -0.08
    ISP
    -0.08
    AdapterManager
    -0.08
    UDO
    -0.08
    ointed
    -0.08
    amus
    -0.08
    IDO
    -0.08
    POSITIVE LOGITS
     used
    0.14
    -based
    0.14
     itself
    0.14
     is
    0.13
     can
    0.12
     has
    0.11
     finds
    0.11
     use
    0.11
     also
    0.11
    used
    0.10
    Act Density 0.018%

    No Known Activations