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

    Neuronpedia

    INDEX
    Explanations

    code/equation delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arters
    -0.06
     famous
    -0.06
    HAS
    -0.06
     irrational
    -0.06
     간
    -0.06
    /cs
    -0.06
     cancers
    -0.06
    間に
    -0.05
     theres
    -0.05
     Samurai
    -0.05
    POSITIVE LOGITS
     statist
    0.06
    _define
    0.06
     cms
    0.06
     Defence
    0.06
     offices
    0.06
     طی
    0.06
    �
    0.06
    .clients
    0.06
    -last
    0.06
     USD
    0.06
    Act Density 0.060%

    No Known Activations