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

    Neuronpedia

    INDEX
    Explanations

    Hubbard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    sans
    -0.07
    luluk
    -0.07
    egrate
    -0.06
     overposting
    -0.06
    NSDate
    -0.06
     celular
    -0.06
     numbering
    -0.06
    payments
    -0.06
    .Aggressive
    -0.06
    inate
    -0.06
    POSITIVE LOGITS
     Hubbard
    0.09
    (db
    0.07
     disc
    0.07
     Kerr
    0.07
     Occ
    0.07
     прис
    0.07
    /hash
    0.07
     nfl
    0.06
     Obama
    0.06
     Public
    0.06
    Act Density 0.001%

    No Known Activations