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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -preview
    -0.07
     DOI
    -0.07
    Angular
    -0.07
     overshadow
    -0.06
     Auckland
    -0.06
    like
    -0.06
     Gew
    -0.06
    .sd
    -0.06
    475
    -0.06
    Shutdown
    -0.06
    POSITIVE LOGITS
    ettings
    0.06
     bian
    0.06
    ór
    0.06
    TRUE
    0.06
    drs
    0.06
     cây
    0.06
     يمكن
    0.06
    étique
    0.06
     (_,
    0.05
     обра
    0.05
    Act Density 0.043%

    No Known Activations