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

    Neuronpedia

    INDEX
    Explanations

    dd

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ：“
    -0.07
    =\"
    -0.07
    _room
    -0.06
    _almost
    -0.06
    (kernel
    -0.06
     Program
    -0.06
     trillion
    -0.06
     türü
    -0.06
    .Login
    -0.06
     узн
    -0.06
    POSITIVE LOGITS
    leftright
    0.07
    etherlands
    0.06
     RENDER
    0.06
    regnum
    0.06
    ndx
    0.06
    WebResponse
    0.06
    _CLAMP
    0.06
    paredStatement
    0.06
    ubl
    0.06
     DISPATCH
    0.06
    Act Density 0.008%

    No Known Activations