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

    Neuronpedia

    INDEX
    Explanations

    creation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marketed
    -0.06
     stud
    -0.06
     Swan
    -0.06
     POLL
    -0.06
     hybrids
    -0.06
     Kia
    -0.06
    "].
    -0.06
    _GAP
    -0.06
    .Misc
    -0.06
     Waste
    -0.06
    POSITIVE LOGITS
     foliage
    0.07
     clicks
    0.07
     дум
    0.07
    /support
    0.06
     deline
    0.06
    ;↵↵↵↵↵
    0.06
    leine
    0.06
     equality
    0.06
    wx
    0.06
    adf
    0.06
    Act Density 0.200%

    No Known Activations