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

    Neuronpedia

    INDEX
    Explanations

    foreign language word fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    角的
    0.58
    ियो
    0.58
    シ
    0.57
     leaderboard
    0.55
    ो
    0.54
    ับ
    0.54
    Storing
    0.52
    ोटा
    0.52
    ഴിഞ്ഞ
    0.52
    ப்படுத்து
    0.52
    POSITIVE LOGITS
    ken
    0.98
    ke
    0.91
    そんな
    0.89
     nende
    0.88
    nsan
    0.87
    ttemberg
    0.87
    np
    0.85
    bst
    0.85
    hlen
    0.85
     Mugabe
    0.84
    Act Density 0.017%

    No Known Activations