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

    Neuronpedia

    INDEX
    Explanations

    danger and safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mnie
    -0.06
    deny
    -0.06
    척
    -0.06
    684
    -0.06
    ��
    -0.06
    .environment
    -0.06
     Latitude
    -0.06
    .restaurant
    -0.06
     serve
    -0.06
     locom
    -0.06
    POSITIVE LOGITS
    ової
    0.07
     їх
    0.07
    _RANK
    0.07
    よう
    0.07
    .ComponentPlacement
    0.07
     『
    0.07
    typedef
    0.06
    <Audio
    0.06
    .AspNet
    0.06
     mét
    0.06
    Act Density 0.908%

    No Known Activations