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

    Neuronpedia

    INDEX
    Explanations

    reversible

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (validate
    -0.07
    傥
    -0.07
     LocalDate
    -0.07
    BUF
    -0.07
    訾
    -0.07
    PN
    -0.07
    }
↵
    -0.07
    lec
    -0.06
    浒
    -0.06
    中国文化
    -0.06
    POSITIVE LOGITS
     reversible
    0.07
    odied
    0.07
     balancing
    0.07
    otion
    0.07
     cyclic
    0.06
    更多的
    0.06
     revers
    0.06
     powering
    0.06
     relev
    0.06
     св
    0.06
    Act Density 0.003%

    No Known Activations