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

    Neuronpedia

    INDEX
    Explanations

    representation theory and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ganglion
    0.48
     labyr
    0.46
     sustent
    0.46
     pdelay
    0.44
    <unused1854>
    0.43
     interstices
    0.43
    ⛲
    0.43
    랫폼
    0.42
    წინ
    0.42
     pudieran
    0.42
    POSITIVE LOGITS
    Represent
    0.70
     Representation
    0.69
    Representation
    0.69
     Representations
    0.64
     Rep
    0.63
    Rep
    0.62
     Represent
    0.57
    representations
    0.55
     representation
    0.55
     rep
    0.54
    Act Density 0.001%

    No Known Activations