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

    Neuronpedia

    INDEX
    Explanations

    punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (customer
    -0.06
    ⌒
    -0.06
    ึ
    -0.06
     conference
    -0.06
     barg
    -0.06
    orrar
    -0.06
     اف
    -0.06
     foremost
    -0.05
    (core
    -0.05
    _topic
    -0.05
    POSITIVE LOGITS
    atedRoute
    0.06
     Sally
    0.06
     Pom
    0.06
     Ін
    0.06
     Sandra
    0.06
     detach
    0.06
     볼
    0.06
    layın
    0.06
     Brun
    0.06
     Jes
    0.06
    Act Density 0.029%

    No Known Activations