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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash

    This neuron spots XML resource definitions by firing on the numeric msgid attributes in Android string‐resource tags.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    같
    -0.07
    ++;↵↵
    -0.07
    (logits
    -0.07
    --;
↵
    -0.07
    )↵↵↵↵↵
    -0.07
    Mvc
    -0.06
    .',
↵
    -0.06
    ']]]↵
    -0.06
    ISC
    -0.06
    />.↵
    -0.06
    POSITIVE LOGITS
     poker
    0.07
     SSR
    0.06
     нього
    0.06
     REV
    0.06
    urrets
    0.06
    lsa
    0.06
     MGM
    0.06
     Civic
    0.06
     Chap
    0.06
     Estados
    0.06
    Act Density 0.004%

    No Known Activations