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

    Neuronpedia

    INDEX
    Explanations

    Korean noun-forming particle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    CORD
    0.40
    kikh
    0.39
    lfloor
    0.38
    іл
    0.38
    Policies
    0.38
    quettes
    0.38
    mest
    0.37
    otov
    0.37
    ESSION
    0.37
    ముల
    0.37
    POSITIVE LOGITS
     위한
    0.53
     위해서는
    0.50
     위해
    0.49
     전에
    0.47
     conducive
    0.46
     incont
    0.45
     handsome
    0.43
     extend
    0.41
     conservar
    0.41
     Vito
    0.41
    Act Density 0.002%

    No Known Activations