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

    Neuronpedia

    INDEX
    Explanations

    necessity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulner
    -0.07
    𫄷
    -0.07
    Α
    -0.06
    妝
    -0.06
    奥林
    -0.06
     Arbeit
    -0.06
     gridBagConstraints
    -0.06
    odyn
    -0.06
    ':['
    -0.06
    MenuStrip
    -0.06
    POSITIVE LOGITS
    initializer
    0.07
    Ship
    0.07
    squeeze
    0.07
    系统的
    0.07
    _position
    0.07
    は何
    0.07
    サイズ
    0.06
     Committee
    0.06
    طبيع
    0.06
     главное
    0.06
    Act Density 0.015%

    No Known Activations