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

    Neuronpedia

    INDEX
    Explanations

    clarification and implementation details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     semiconductor
    0.40
    υχ
    0.38
     biom
    0.38
     وقد
    0.36
     chromosomal
    0.35
     rearrangement
    0.35
     phylogeny
    0.35
     cardiovascular
    0.35
     Tim
    0.35
     Kry
    0.35
    POSITIVE LOGITS
    Highway
    0.48
    C
    0.48
    Ware
    0.46
    Sche
    0.45
    で
    0.44
    sizer
    0.44
    Invoice
    0.43
    约
    0.43
    From
    0.42
    Pixels
    0.42
    Act Density 0.005%

    No Known Activations