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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    殷
    0.41
    okie
    0.38
    nego
    0.37
    pert
    0.35
    štu
    0.35
    دى
    0.35
    hWnd
    0.35
    EW
    0.35
    fl
    0.35
    朱
    0.35
    POSITIVE LOGITS
    tooltip
    0.94
     tooltip
    0.83
    Tooltip
    0.82
    dropdown
    0.61
    ToolTip
    0.55
     Modal
    0.51
    Dropdown
    0.50
    modal
    0.49
    Popover
    0.49
    Modal
    0.47
    Act Density 0.004%

    No Known Activations