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

    Neuronpedia

    INDEX
    Explanations

    math equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    通信
    -0.06
    ULA
    -0.06
    ्पष
    -0.06
    .xyz
    -0.06
    acles
    -0.06
     authentication
    -0.06
     Dal
    -0.06
    ึง
    -0.06
    USTER
    -0.06
    (surface
    -0.06
    POSITIVE LOGITS
     tainted
    0.07
    appe
    0.06
    REGION
    0.06
     wh
    0.06
    Contr
    0.06
    İng
    0.06
    ISTRIBUT
    0.06
     navbar
    0.06
    λαν
    0.06
    Endian
    0.06
    Act Density 0.017%

    No Known Activations