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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cardboard
    -0.07
     recip
    -0.07
    ;',↵
    -0.07
    '][$
    -0.06
    Trip
    -0.06
     bright
    -0.06
    Sean
    -0.06
    /test
    -0.06
    hop
    -0.06
     comme
    -0.06
    POSITIVE LOGITS
     Problem
    0.07
     mileage
    0.06
    (jsonPath
    0.06
    gra
    0.06
     Toilet
    0.06
    เวลา
    0.06
     plumber
    0.06
     Walls
    0.06
    ovatel
    0.06
    otherapy
    0.06
    Act Density 0.000%

    No Known Activations