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

    Neuronpedia

    INDEX
    Explanations

    but

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Lace
    -0.07
    cakes
    -0.06
    erties
    -0.06
    ibName
    -0.06
     merry
    -0.06
     ordeal
    -0.06
     mower
    -0.06
     Nancy
    -0.06
    .getChild
    -0.06
     aussi
    -0.06
    POSITIVE LOGITS
     перер
    0.07
    .linkedin
    0.07
     highlighted
    0.07
     фот
    0.07
    /desktop
    0.06
     '');↵
    0.06
    .management
    0.06
     fleets
    0.06
    ）↵
    0.06
    _check
    0.06
    Act Density 0.002%

    No Known Activations