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

    Neuronpedia

    INDEX
    Explanations

    alliteration of A adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     누가
    0.57
    ผู้
    0.57
     Studie
    0.52
     considéré
    0.51
     Convenience
    0.51
    𝗝
    0.50
     NGO
    0.50
     적극
    0.50
    非常有
    0.50
     tzv
    0.49
    POSITIVE LOGITS
    aspect
    0.56
    brushes
    0.56
    new
    0.55
    with
    0.54
    ؟
    0.54
    veh
    0.53
    swith
    0.53
    balls
    0.53
    leather
    0.53
    fluid
    0.52
    Act Density 0.013%

    No Known Activations