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

    Neuronpedia

    INDEX
    Explanations

    based on or like

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    êng
    0.22
     내용은
    0.20
    énération
    0.19
    opy
    0.19
    น์โหลด
    0.19
     함수의
    0.19
    ü
    0.19
     구분
    0.19
    öglichkeiten
    0.18
    รายละเอียด
    0.18
    POSITIVE LOGITS
    based
    0.56
    related
    0.47
     based
    0.40
    driven
    0.40
     आधारित
    0.39
    Based
    0.39
    derived
    0.39
    inspired
    0.39
    induced
    0.38
     centric
    0.38
    Act Density 0.144%

    No Known Activations