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

    Neuronpedia

    INDEX
    Explanations

    seen before

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     human
    0.46
     moder
    0.46
     positiv
    0.46
     toler
    0.45
     učen
    0.43
     positive
    0.43
     contributes
    0.42
     motivación
    0.42
     promover
    0.42
     bioactive
    0.42
    POSITIVE LOGITS
    ссий
    0.39
     বিতরণ
    0.38
     వద్ద
    0.38
    ње
    0.38
     প্রথমে
    0.38
     INITIAL
    0.38
    бычно
    0.38
     முதலில்
    0.38
    лежа
    0.37
    RIG
    0.37
    Act Density 0.001%

    No Known Activations