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

    Neuronpedia

    INDEX
    Explanations

    sounds like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     doméstica
    0.38
    祝い
    0.38
    মোঃ
    0.37
    <footer>
    0.37
     Kong
    0.36
    山东
    0.36
    clustering
    0.36
    Microsoft
    0.36
    宿泊
    0.36
    ुआ
    0.36
    POSITIVE LOGITS
     অথবা
    0.44
     또는
    0.43
     或者
    0.43
     metaphors
    0.42
     または
    0.42
    nab
    0.41
     jeho
    0.41
     jego
    0.40
     desg
    0.40
     onslaught
    0.40
    Act Density 0.001%

    No Known Activations