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

    Neuronpedia

    INDEX
    Explanations

    html title tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    нары
    1.00
     thatched
    1.00
     branchNode
    0.97
     sulfon
    0.95
     audiovisual
    0.93
     biogas
    0.91
     tombs
    0.90
     colorectal
    0.90
     geospatial
    0.90
     ellipses
    0.89
    POSITIVE LOGITS
    ú
    0.85
    5
    0.83
    |,
    0.81
    3
    0.80
    1
    0.76
    |\
    0.74
    what
    0.74
    block
    0.73
    9
    0.73
    q
    0.72
    Act Density 0.001%

    No Known Activations