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

    Neuronpedia

    INDEX
    Explanations

    boolean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UpdateTime
    -0.08
    (\"
    -0.07
     NOTICE
    -0.07
     St
    -0.07
    _Menu
    -0.07
    -my
    -0.06
    -left
    -0.06
    !I
    -0.06
     treatments
    -0.06
    _unref
    -0.06
    POSITIVE LOGITS
    <len
    0.08
     kontrol
    0.07
     ξ
    0.07
    пон
    0.06
    ським
    0.06
    True
    0.06
    <Boolean
    0.06
     เ�
    0.06
    _NEG
    0.06
     способом
    0.06
    Act Density 0.211%

    No Known Activations