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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Там
    -0.07
    oruč
    -0.07
    ajas
    -0.06
     LAW
    -0.06
    \Core
    -0.06
     creo
    -0.06
     symbolic
    -0.06
     merit
    -0.06
     Publications
    -0.06
    еться
    -0.06
    POSITIVE LOGITS
     somehow
    0.07
    弃
    0.06
    .emit
    0.06
    FieldValue
    0.06
    .reload
    0.06
    _hover
    0.06
    ipples
    0.06
    横
    0.06
    InternalServerError
    0.06
     serialization
    0.06
    Act Density 0.056%

    No Known Activations