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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    })",
    -0.07
    ypes
    -0.07
    -effect
    -0.07
    _TYP
    -0.07
     використовувати
    -0.07
    !I
    -0.07
    .dist
    -0.06
    ğın
    -0.06
     hasNext
    -0.06
     TokenType
    -0.06
    POSITIVE LOGITS
     server
    0.07
    _quad
    0.06
    DATA
    0.06
    host
    0.06
    /thread
    0.06
    _node
    0.06
    -network
    0.06
    عدد
    0.06
    embedded
    0.06
    SERVICE
    0.06
    Act Density 0.035%

    No Known Activations