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

    Neuronpedia

    INDEX
    Explanations

    academic doi links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wikimedia
    0.42
    年輕
    0.42
    사는
    0.42
     Stripe
    0.41
    गोर
    0.41
    ギラ
    0.41
     উইকেট
    0.41
    ৳
    0.40
     Министерства
    0.40
     તથા
    0.39
    POSITIVE LOGITS
     dx
    0.79
    dx
    0.74
    DX
    0.62
    Dx
    0.58
     DX
    0.57
     Dx
    0.56
    doi
    0.50
     doi
    0.49
     DOI
    0.49
     dy
    0.45
    Act Density 0.000%

    No Known Activations