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

    Neuronpedia

    INDEX
    Explanations

    code or equations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oppers
    -0.06
     TVs
    -0.06
     secondary
    -0.06
    dots
    -0.06
    -buttons
    -0.06
     والد
    -0.06
     другого
    -0.06
     Barry
    -0.06
     leftovers
    -0.06
    759
    -0.06
    POSITIVE LOGITS
    …"↵↵
    0.06
    _G
    0.06
    (=
    0.06
     complying
    0.06
    getPage
    0.06
    _proto
    0.06
     Rt
    0.06
     cosmic
    0.06
    mpl
    0.06
    ubuntu
    0.06
    Act Density 0.022%

    No Known Activations