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

    Neuronpedia

    INDEX
    Explanations

    Mary Poppins

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =====
    -0.08
    Spoiler
    -0.06
    }
↵
↵
↵
↵
    -0.06
    (rotation
    -0.06
     precision
    -0.06
    ाल
    -0.06
    audit
    -0.06
    답
    -0.06
    ΙΛ
    -0.06
    一些
    -0.06
    POSITIVE LOGITS
     verbal
    0.07
     Jersey
    0.06
    jours
    0.06
    _cross
    0.06
    .IOException
    0.06
    (core
    0.06
     umb
    0.06
     bfd
    0.06
     chín
    0.06
     conc
    0.06
    Act Density 0.003%

    No Known Activations