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

    Neuronpedia

    INDEX
    Explanations

    blockage, obstruction, or buildup

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    informed
    0.51
     Emerging
    0.50
    W
    0.49
    il
    0.49
    zi
    0.47
    Z
    0.47
    in
    0.47
     Z
    0.46
    T
    0.45
    ющие
    0.45
    POSITIVE LOGITS
    阻塞
    0.63
     obstru
    0.63
     causada
    0.63
     obstructions
    0.59
     clogged
    0.59
     blockage
    0.55
     situa
    0.55
     veroor
    0.54
     caused
    0.54
     arteries
    0.53
    Act Density 0.211%

    No Known Activations