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

    Neuronpedia

    INDEX
    Explanations

    code and queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    972
    -0.08
    изма
    -0.07
    ована
    -0.07
     ки
    -0.07
     Cer
    -0.07
     брос
    -0.07
     вол
    -0.07
     vuestro
    -0.07
    ,System
    -0.07
    -en
    -0.07
    POSITIVE LOGITS
     afterward
    0.12
     afterwards
    0.11
     thereafter
    0.11
     posteriores
    0.09
     Afterwards
    0.09
     retrieval
    0.09
     teardown
    0.09
     subsequent
    0.09
     조회
    0.09
     querying
    0.08
    Act Density 0.047%

    No Known Activations