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

    Neuronpedia

    INDEX
    Explanations

    advice and common sense

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .engine
    -0.07
    _WAKE
    -0.07
    Parcelable
    -0.07
     کنار
    -0.06
    اسة
    -0.06
     linh
    -0.06
     Raptors
    -0.06
    (Level
    -0.06
     नए
    -0.06
    foo
    -0.06
    POSITIVE LOGITS
    dı
    0.07
    があった
    0.06
    네
    0.06
    _IE
    0.06
    alamat
    0.06
    working
    0.06
    zim
    0.06
     deceive
    0.06
    BAD
    0.06
     indir
    0.06
    Act Density 0.116%

    No Known Activations