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

    Neuronpedia

    INDEX
    Explanations

    compressor

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wine
    -0.08
     Wine
    -0.07
     Drinks
    -0.07
    _digits
    -0.06
     hiding
    -0.06
    Todos
    -0.06
     dolphins
    -0.06
    -mouth
    -0.06
     pops
    -0.06
    mites
    -0.06
    POSITIVE LOGITS
    <html
    0.06
     ал
    0.06
     Perm
    0.06
    .Ordinal
    0.06
    ام
    0.06
    stateProvider
    0.06
    ！↵
    0.06
     التاريخ
    0.06
    改革
    0.06
    standen
    0.06
    Act Density 0.005%

    No Known Activations