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

    Neuronpedia

    INDEX
    Explanations

    Arashiyama

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SOM
    0.53
     som
    0.50
    Som
    0.49
     Som
    0.48
     Somerset
    0.48
     Somali
    0.48
     Somalia
    0.46
    ワー
    0.45
    som
    0.43
     み
    0.42
    POSITIVE LOGITS
     oo
    0.55
    adaya
    0.54
    eyn
    0.52
    estay
    0.50
    atay
    0.50
    eya
    0.49
    ash
    0.49
    leys
    0.48
    siye
    0.48
    si
    0.47
    Act Density 0.000%

    No Known Activations