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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     인정
    -0.07
    itness
    -0.07
    Retail
    -0.07
     長
    -0.06
     Tok
    -0.06
    .Parcel
    -0.06
    Muslim
    -0.06
     dwarf
    -0.06
     Twitch
    -0.06
    _PACKET
    -0.06
    POSITIVE LOGITS
     đáng
    0.08
    eni
    0.07
     सल
    0.07
    ：</
    0.06
    ~~~~
    0.06
     carc
    0.06
    Hostname
    0.06
    etti
    0.06
    ンティ
    0.06
     Eb
    0.06
    Act Density 0.022%

    No Known Activations