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

    Neuronpedia

    INDEX
    Explanations

    assemble sprint

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wrapper
    0.53
     contacting
    0.49
     Sketches
    0.49
    +}(
    0.47
     및
    0.46
     calculer
    0.46
    姓
    0.45
    ড্রিম
    0.44
     Architect
    0.44
     bakteri
    0.44
    POSITIVE LOGITS
    aren
    0.45
    ab
    0.45
    ante
    0.45
    1
    0.43
    лю
    0.43
    ES
    0.42
    AKE
    0.42
    ei
    0.42
    ¯
    0.42
    éb
    0.41
    Act Density 0.001%

    No Known Activations