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

    Neuronpedia

    INDEX
    Explanations

    in the UK

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     BoxFit
    0.45
     Syndrome
    0.40
    திகளை
    0.40
     Kt
    0.39
     కి
    0.38
     Prisma
    0.36
    iliano
    0.36
    iket
    0.35
    猚
    0.35
     Postal
    0.35
    POSITIVE LOGITS
    氘
    0.48
    Spar
    0.41
     Sparrow
    0.39
    Sw
    0.37
     Spar
    0.37
     gossip
    0.36
    QUERY
    0.35
    λαβ
    0.35
     Eel
    0.35
     Nile
    0.35
    Act Density 0.013%

    No Known Activations