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

    Neuronpedia

    INDEX
    Explanations

    check or cross off items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ProductId
    -0.91
    asting
    -0.80
    Latch
    -0.80
     Produits
    -0.79
     callable
    -0.78
     ANYTHING
    -0.76
    addChild
    -0.73
     JUMP
    -0.72
    NPs
    -0.72
    ¤
    -0.72
    POSITIVE LOGITS
     boxes
    2.75
     box
    2.02
     ticks
    1.98
     tick
    1.94
    boxes
    1.91
    Boxes
    1.88
     Boxes
    1.86
     ticked
    1.72
     checkbox
    1.61
     Box
    1.48
    Act Density 0.012%

    No Known Activations