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

    Neuronpedia

    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slight
    -0.07
    prt
    -0.07
     delight
    -0.07
    right
    -0.07
     isolated
    -0.07
    ierte
    -0.06
     explode
    -0.06
    losing
    -0.06
     obligated
    -0.06
     io
    -0.06
    POSITIVE LOGITS
     Campus
    0.15
     campus
    0.14
    ampus
    0.09
     campuses
    0.07
     Campbell
    0.07
     Autodesk
    0.07
     슈
    0.07
     Workplace
    0.07
    aptop
    0.07
     ocas
    0.07
    Act Density 0.002%

    No Known Activations