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

    Neuronpedia

    INDEX
    Explanations

    Cloud environment, crypto landscape

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     အရ
    0.53
     tacos
    0.52
     간단
    0.49
     인해
    0.49
     Taxes
    0.48
     Attic
    0.47
     Liquor
    0.46
     자동
    0.45
     Taco
    0.45
     kaise
    0.45
    POSITIVE LOGITS
    möglich
    0.50
    лл
    0.47
    ầm
    0.46
    ៥
    0.44
    zęd
    0.44
    ное
    0.43
     Hoffnung
    0.43
     nejen
    0.43
    ميم
    0.43
    istatic
    0.43
    Act Density 0.001%

    No Known Activations