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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蜀
    -0.08
     morph
    -0.07
    乡土
    -0.07
     roadmap
    -0.07
     fundra
    -0.07
    .valid
    -0.07
    𝖊
    -0.07
     succ
    -0.07
     Ter
    -0.07
    טר
    -0.07
    POSITIVE LOGITS
    WebResponse
    0.07
    dsn
    0.07
     niezbędn
    0.07
    objects
    0.07
     Listening
    0.07
     zarówno
    0.07
    GS
    0.06
     Wallet
    0.06
    看法
    0.06
     gear
    0.06
    Act Density 0.001%

    No Known Activations