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

    Neuronpedia

    INDEX
    Explanations

    css pseudo-classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     الفور
    0.44
     taip
    0.40
    ล็
    0.37
     মশ
    0.37
     συνα
    0.35
     відді
    0.35
     ET
    0.35
     பரி
    0.35
     raisons
    0.35
     تعیین
    0.34
    POSITIVE LOGITS
    nth
    0.79
    hover
    0.73
    Hover
    0.72
     hover
    0.72
     nth
    0.62
     Hover
    0.59
    not
    0.54
     hovered
    0.54
    target
    0.50
     not
    0.49
    Act Density 0.002%

    No Known Activations