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

    Neuronpedia

    INDEX
    Explanations

    data structures, types, service configurations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     IDE
    0.38
     own
    0.38
     deafness
    0.36
     mph
    0.35
     acept
    0.35
     optimal
    0.34
     yht
    0.34
     iht
    0.34
     nag
    0.34
     sortBy
    0.34
    POSITIVE LOGITS
     ਉਸ
    0.37
    PERATURE
    0.37
    omeres
    0.37
    oden
    0.37
    porta
    0.35
     جس
    0.35
    mero
    0.34
    chromo
    0.34
    galactos
    0.34
    ังหวัด
    0.34
    Act Density 0.000%

    No Known Activations