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

    Neuronpedia

    INDEX
    Explanations

    Gun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (QtCore
    -0.08
    ximo
    -0.07
     stadiums
    -0.07
    ✍
    -0.07
     distract
    -0.07
     adım
    -0.07
     тре
    -0.07
     Cruise
    -0.07
    TabIndex
    -0.07
     theaters
    -0.07
    POSITIVE LOGITS
     gun
    0.08
    ɴ
    0.07
    印刷
    0.07
    唧
    0.07
     natural
    0.07
    _named
    0.07
     Mines
    0.06
     организ
    0.06
     and
    0.06
    柱
    0.06
    Act Density 0.008%

    No Known Activations