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

    Neuronpedia

    INDEX
    Explanations

    value of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    イン
    0.49
     ので
    0.41
    Therefore
    0.39
    THE
    0.39
    FOUND
    0.39
     بينا
    0.38
    COMP
    0.38
    위
    0.38
    Lovely
    0.37
     ervoor
    0.37
    POSITIVE LOGITS
    ̽
    0.42
    时间和
    0.42
     Newspapers
    0.41
     Nucl
    0.40
     Friendship
    0.40
     eco
    0.38
     लाइफ
    0.38
     युवाओं
    0.38
    结束后
    0.38
     bienn
    0.38
    Act Density 0.003%

    No Known Activations