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

    Neuronpedia

    INDEX
    Explanations

    lists and definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     notebooks
    0.53
     nightmares
    0.50
     noodles
    0.46
     hedon
    0.46
     electrical
    0.45
     시간에
    0.45
     flashbacks
    0.44
     windfall
    0.43
     haircuts
    0.43
     ప్
    0.42
    POSITIVE LOGITS
     शोक
    0.43
    ºC
    0.41
    った
    0.41
    uolo
    0.40
    irt
    0.40
    ntgen
    0.40
     équipe
    0.39
     umfasst
    0.39
    ir
    0.39
    টার
    0.39
    Act Density 0.007%

    No Known Activations