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

    Neuronpedia

    INDEX
    Explanations

    author names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Hogwarts
    0.61
     SUVs
    0.59
     Nantucket
    0.57
     Fonbet
    0.55
     Mesopotamia
    0.55
     CXCR
    0.55
     Diageo
    0.55
     दुनियाभर
    0.54
     Inquisition
    0.54
     Invisalign
    0.54
    POSITIVE LOGITS
     I
    0.46
    -
    0.46
     J
    0.45
    0.43
     C
    0.43
     W
    0.42
     del
    0.42
     de
    0.41
     R
    0.40
     van
    0.39
    Act Density 0.001%

    No Known Activations