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

    Neuronpedia

    INDEX
    Explanations

    μ

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     partir
    -0.07
    누
    -0.06
     bias
    -0.06
     Rider
    -0.06
    oter
    -0.06
     Snape
    -0.06
    αρα
    -0.06
     terminator
    -0.06
    َا
    -0.06
     Voters
    -0.06
    POSITIVE LOGITS
     çok
    0.07
    _bitmap
    0.06
    Shoot
    0.06
    URITY
    0.06
    <DateTime
    0.06
    :CGPoint
    0.06
     punishing
    0.06
    ất
    0.06
     UNIVERSITY
    0.06
     ;;↵
    0.06
    Act Density 0.001%

    No Known Activations