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

    Neuronpedia

    INDEX
    Explanations

    places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     island
    0.63
    island
    0.61
    Island
    0.55
     ISLAND
    0.49
     pulau
    0.47
     Island
    0.46
    岛
    0.44
    Prince
    0.43
     দ্বীপ
    0.42
     Prince
    0.41
    POSITIVE LOGITS
     Atl
    0.44
    ષ્
    0.41
    /+
    0.40
     sump
    0.40
     '+'
    0.40
     thrombo
    0.40
     colourful
    0.40
     an
    0.40
     neder
    0.40
     aan
    0.39
    Act Density 0.000%

    No Known Activations