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

    Neuronpedia

    INDEX
    Explanations

    incorporate

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commons
    -0.06
     stamps
    -0.06
     equation
    -0.06
    ’aut
    -0.06
     placebo
    -0.06
    rx
    -0.06
     passed
    -0.06
    sched
    -0.06
     wax
    -0.06
     equals
    -0.06
    POSITIVE LOGITS
     Incorpor
    0.19
     incorpor
    0.11
     Incorporated
    0.08
     incorporation
    0.07
     Willie
    0.07
     Arap
    0.06
    ectors
    0.06
     problémy
    0.06
    awai
    0.06
     вико
    0.06
    Act Density 0.002%

    No Known Activations